Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–30 of 30 results for author: <span class="mathjax">Azaria, A</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Azaria%2C+A">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Azaria, A"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Azaria%2C+A&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Azaria, A"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.17460">arXiv:2404.17460</a> <span> [<a href="https://arxiv.org/pdf/2404.17460">pdf</a>, <a href="https://arxiv.org/format/2404.17460">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Ruffle&Riley: Insights from Designing and Evaluating a Large Language Model-Based Conversational Tutoring System </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Schmucker%2C+R">Robin Schmucker</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+M">Meng Xia</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Mitchell%2C+T">Tom Mitchell</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.17460v1-abstract-short" style="display: inline;"> Conversational tutoring systems (CTSs) offer learning experiences through interactions based on natural language. They are recognized for promoting cognitive engagement and improving learning outcomes, especially in reasoning tasks. Nonetheless, the cost associated with authoring CTS content is a major obstacle to widespread adoption and to research on effective instructional design. In this paper… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.17460v1-abstract-full').style.display = 'inline'; document.getElementById('2404.17460v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.17460v1-abstract-full" style="display: none;"> Conversational tutoring systems (CTSs) offer learning experiences through interactions based on natural language. They are recognized for promoting cognitive engagement and improving learning outcomes, especially in reasoning tasks. Nonetheless, the cost associated with authoring CTS content is a major obstacle to widespread adoption and to research on effective instructional design. In this paper, we discuss and evaluate a novel type of CTS that leverages recent advances in large language models (LLMs) in two ways: First, the system enables AI-assisted content authoring by inducing an easily editable tutoring script automatically from a lesson text. Second, the system automates the script orchestration in a learning-by-teaching format via two LLM-based agents (Ruffle&Riley) acting as a student and a professor. The system allows for free-form conversations that follow the ITS-typical inner and outer loop structure. We evaluate Ruffle&Riley's ability to support biology lessons in two between-subject online user studies (N = 200) comparing the system to simpler QA chatbots and reading activity. Analyzing system usage patterns, pre/post-test scores and user experience surveys, we find that Ruffle&Riley users report high levels of engagement, understanding and perceive the offered support as helpful. Even though Ruffle&Riley users require more time to complete the activity, we did not find significant differences in short-term learning gains over the reading activity. Our system architecture and user study provide various insights for designers of future CTSs. We further open-source our system to support ongoing research on effective instructional design of LLM-based learning technologies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.17460v1-abstract-full').style.display = 'none'; document.getElementById('2404.17460v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: substantial text overlap with arXiv:2310.01420</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.11330">arXiv:2401.11330</a> <span> [<a href="https://arxiv.org/pdf/2401.11330">pdf</a>, <a href="https://arxiv.org/format/2401.11330">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Source Detection in Networks using the Stationary Distribution of a Markov Chain </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sabato%2C+Y">Yael Sabato</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Hazon%2C+N">Noam Hazon</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.11330v1-abstract-short" style="display: inline;"> Nowadays, the diffusion of information through social networks is a powerful phenomenon. One common way to model diffusions in social networks is the Independent Cascade (IC) model. Given a set of infected nodes according to the IC model, a natural problem is the source detection problem, in which the goal is to identify the unique node that has started the diffusion. Maximum Likelihood Estimation… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11330v1-abstract-full').style.display = 'inline'; document.getElementById('2401.11330v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.11330v1-abstract-full" style="display: none;"> Nowadays, the diffusion of information through social networks is a powerful phenomenon. One common way to model diffusions in social networks is the Independent Cascade (IC) model. Given a set of infected nodes according to the IC model, a natural problem is the source detection problem, in which the goal is to identify the unique node that has started the diffusion. Maximum Likelihood Estimation (MLE) is a common approach for tackling the source detection problem, but it is computationally hard. In this work, we propose an efficient method for the source detection problem under the MLE approach, which is based on computing the stationary distribution of a Markov chain. Using simulations, we demonstrate the effectiveness of our method compared to other state-of-the-art methods from the literature, both on random and real-world networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11330v1-abstract-full').style.display = 'none'; document.getElementById('2401.11330v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.01420">arXiv:2310.01420</a> <span> [<a href="https://arxiv.org/pdf/2310.01420">pdf</a>, <a href="https://arxiv.org/format/2310.01420">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Ruffle&Riley: Towards the Automated Induction of Conversational Tutoring Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Schmucker%2C+R">Robin Schmucker</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+M">Meng Xia</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Mitchell%2C+T">Tom Mitchell</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.01420v2-abstract-short" style="display: inline;"> Conversational tutoring systems (CTSs) offer learning experiences driven by natural language interaction. They are known to promote high levels of cognitive engagement and benefit learning outcomes, particularly in reasoning tasks. Nonetheless, the time and cost required to author CTS content is a major obstacle to widespread adoption. In this paper, we introduce a novel type of CTS that leverages… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.01420v2-abstract-full').style.display = 'inline'; document.getElementById('2310.01420v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.01420v2-abstract-full" style="display: none;"> Conversational tutoring systems (CTSs) offer learning experiences driven by natural language interaction. They are known to promote high levels of cognitive engagement and benefit learning outcomes, particularly in reasoning tasks. Nonetheless, the time and cost required to author CTS content is a major obstacle to widespread adoption. In this paper, we introduce a novel type of CTS that leverages the recent advances in large language models (LLMs) in two ways: First, the system induces a tutoring script automatically from a lesson text. Second, the system automates the script orchestration via two LLM-based agents (Ruffle&Riley) with the roles of a student and a professor in a learning-by-teaching format. The system allows a free-form conversation that follows the ITS-typical inner and outer loop structure. In an initial between-subject online user study (N = 100) comparing Ruffle&Riley to simpler QA chatbots and reading activity, we found no significant differences in post-test scores. Nonetheless, in the learning experience survey, Ruffle&Riley users expressed higher ratings of understanding and remembering and further perceived the offered support as more helpful and the conversation as coherent. Our study provides insights for a new generation of scalable CTS technologies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.01420v2-abstract-full').style.display = 'none'; document.getElementById('2310.01420v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NeurIPS'23 GAIED, Camera-ready</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.08625">arXiv:2309.08625</a> <span> [<a href="https://arxiv.org/pdf/2309.08625">pdf</a>, <a href="https://arxiv.org/format/2309.08625">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Performance of ChatGPT-3.5 and GPT-4 on the United States Medical Licensing Examination With and Without Distractions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Safrai%2C+M">Myriam Safrai</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.08625v1-abstract-short" style="display: inline;"> As Large Language Models (LLMs) are predictive models building their response based on the words in the prompts, there is a risk that small talk and irrelevant information may alter the response and the suggestion given. Therefore, this study aims to investigate the impact of medical data mixed with small talk on the accuracy of medical advice provided by ChatGPT. USMLE step 3 questions were used… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08625v1-abstract-full').style.display = 'inline'; document.getElementById('2309.08625v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.08625v1-abstract-full" style="display: none;"> As Large Language Models (LLMs) are predictive models building their response based on the words in the prompts, there is a risk that small talk and irrelevant information may alter the response and the suggestion given. Therefore, this study aims to investigate the impact of medical data mixed with small talk on the accuracy of medical advice provided by ChatGPT. USMLE step 3 questions were used as a model for relevant medical data. We use both multiple choice and open ended questions. We gathered small talk sentences from human participants using the Mechanical Turk platform. Both sets of USLME questions were arranged in a pattern where each sentence from the original questions was followed by a small talk sentence. ChatGPT 3.5 and 4 were asked to answer both sets of questions with and without the small talk sentences. A board-certified physician analyzed the answers by ChatGPT and compared them to the formal correct answer. The analysis results demonstrate that the ability of ChatGPT-3.5 to answer correctly was impaired when small talk was added to medical data for multiple-choice questions (72.1\% vs. 68.9\%) and open questions (61.5\% vs. 44.3\%; p=0.01), respectively. In contrast, small talk phrases did not impair ChatGPT-4 ability in both types of questions (83.6\% and 66.2\%, respectively). According to these results, ChatGPT-4 seems more accurate than the earlier 3.5 version, and it appears that small talk does not impair its capability to provide medical recommendations. Our results are an important first step in understanding the potential and limitations of utilizing ChatGPT and other LLMs for physician-patient interactions, which include casual conversations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08625v1-abstract-full').style.display = 'none'; document.getElementById('2309.08625v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">We release a dataset along with this paper</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.03102">arXiv:2306.03102</a> <span> [<a href="https://arxiv.org/pdf/2306.03102">pdf</a>, <a href="https://arxiv.org/format/2306.03102">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> ChatGPT is a Remarkable Tool -- For Experts </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Azoulay%2C+R">Rina Azoulay</a>, <a href="/search/cs?searchtype=author&query=Reches%2C+S">Shulamit Reches</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.03102v1-abstract-short" style="display: inline;"> This paper investigates the capabilities of ChatGPT as an automated assistant in diverse domains, including scientific writing, mathematics, education, programming, and healthcare. We explore the potential of ChatGPT to enhance productivity, streamline problem-solving processes, and improve writing style. Furthermore, we highlight the potential risks associated with excessive reliance on ChatGPT i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.03102v1-abstract-full').style.display = 'inline'; document.getElementById('2306.03102v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.03102v1-abstract-full" style="display: none;"> This paper investigates the capabilities of ChatGPT as an automated assistant in diverse domains, including scientific writing, mathematics, education, programming, and healthcare. We explore the potential of ChatGPT to enhance productivity, streamline problem-solving processes, and improve writing style. Furthermore, we highlight the potential risks associated with excessive reliance on ChatGPT in these fields. These limitations encompass factors like incorrect and fictitious responses, inaccuracies in code, limited logical reasoning abilities, overconfidence, and critical ethical concerns of copyrights and privacy violation. We outline areas and objectives where ChatGPT proves beneficial, applications where it should be used judiciously, and scenarios where its reliability may be limited. In light of observed limitations, and given that the tool's fundamental errors may pose a special challenge for non-experts, ChatGPT should be used with a strategic methodology. By drawing from comprehensive experimental studies, we offer methods and flow charts for effectively using ChatGPT. Our recommendations emphasize iterative interaction with ChatGPT and independent verification of its outputs. Considering the importance of utilizing ChatGPT judiciously and with expertise, we recommend its usage for experts who are well-versed in the respective domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.03102v1-abstract-full').style.display = 'none'; document.getElementById('2306.03102v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.01378">arXiv:2306.01378</a> <span> [<a href="https://arxiv.org/pdf/2306.01378">pdf</a>, <a href="https://arxiv.org/format/2306.01378">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> </div> </div> <p class="title is-5 mathjax"> Coalition Formation with Bounded Coalition Size </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Levinger%2C+C">Chaya Levinger</a>, <a href="/search/cs?searchtype=author&query=Hazon%2C+N">Noam Hazon</a>, <a href="/search/cs?searchtype=author&query=Simola%2C+S">Sofia Simola</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.01378v2-abstract-short" style="display: inline;"> In many situations when people are assigned to coalitions, the utility of each person depends on the friends in her coalition. Additionally, in many situations, the size of each coalition should be bounded. This paper studies such coalition formation scenarios in both weighted and unweighted settings. Since finding a partition that maximizes the utilitarian social welfare is computationally hard,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.01378v2-abstract-full').style.display = 'inline'; document.getElementById('2306.01378v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.01378v2-abstract-full" style="display: none;"> In many situations when people are assigned to coalitions, the utility of each person depends on the friends in her coalition. Additionally, in many situations, the size of each coalition should be bounded. This paper studies such coalition formation scenarios in both weighted and unweighted settings. Since finding a partition that maximizes the utilitarian social welfare is computationally hard, we provide a polynomial-time approximation algorithm. We also investigate the existence and the complexity of finding stable partitions. Namely, we show that the Contractual Strict Core (CSC) is never empty, but the Strict Core (SC) of some games is empty. Finding partitions that are in the CSC is computationally easy, but even deciding whether an SC of a given game exists is NP-hard. The analysis of the core is more involved. In the unweighted setting, we show that when the coalition size is bounded by 3 the core is never empty, and we present a polynomial time algorithm for finding a member of the core. However, for the weighted setting, the core may be empty, and we prove that deciding whether there exists a core is NP-hard. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.01378v2-abstract-full').style.display = 'none'; document.getElementById('2306.01378v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To be published in AAMAS-24</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.11 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.15486">arXiv:2305.15486</a> <span> [<a href="https://arxiv.org/pdf/2305.15486">pdf</a>, <a href="https://arxiv.org/format/2305.15486">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> SPRING: Studying the Paper and Reasoning to Play Games </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yue Wu</a>, <a href="/search/cs?searchtype=author&query=Prabhumoye%2C+S">Shrimai Prabhumoye</a>, <a href="/search/cs?searchtype=author&query=Min%2C+S+Y">So Yeon Min</a>, <a href="/search/cs?searchtype=author&query=Bisk%2C+Y">Yonatan Bisk</a>, <a href="/search/cs?searchtype=author&query=Salakhutdinov%2C+R">Ruslan Salakhutdinov</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Mitchell%2C+T">Tom Mitchell</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuanzhi Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.15486v3-abstract-short" style="display: inline;"> Open-world survival games pose significant challenges for AI algorithms due to their multi-tasking, deep exploration, and goal prioritization requirements. Despite reinforcement learning (RL) being popular for solving games, its high sample complexity limits its effectiveness in complex open-world games like Crafter or Minecraft. We propose a novel approach, SPRING, to read the game's original aca… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.15486v3-abstract-full').style.display = 'inline'; document.getElementById('2305.15486v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.15486v3-abstract-full" style="display: none;"> Open-world survival games pose significant challenges for AI algorithms due to their multi-tasking, deep exploration, and goal prioritization requirements. Despite reinforcement learning (RL) being popular for solving games, its high sample complexity limits its effectiveness in complex open-world games like Crafter or Minecraft. We propose a novel approach, SPRING, to read the game's original academic paper and use the knowledge learned to reason and play the game through a large language model (LLM). Prompted with the LaTeX source as game context and a description of the agent's current observation, our SPRING framework employs a directed acyclic graph (DAG) with game-related questions as nodes and dependencies as edges. We identify the optimal action to take in the environment by traversing the DAG and calculating LLM responses for each node in topological order, with the LLM's answer to final node directly translating to environment actions. In our experiments, we study the quality of in-context "reasoning" induced by different forms of prompts under the setting of the Crafter open-world environment. Our experiments suggest that LLMs, when prompted with consistent chain-of-thought, have great potential in completing sophisticated high-level trajectories. Quantitatively, SPRING with GPT-4 outperforms all state-of-the-art RL baselines, trained for 1M steps, without any training. Finally, we show the potential of games as a test bed for LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.15486v3-abstract-full').style.display = 'none'; document.getElementById('2305.15486v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.02412">arXiv:2305.02412</a> <span> [<a href="https://arxiv.org/pdf/2305.02412">pdf</a>, <a href="https://arxiv.org/format/2305.02412">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yue Wu</a>, <a href="/search/cs?searchtype=author&query=Min%2C+S+Y">So Yeon Min</a>, <a href="/search/cs?searchtype=author&query=Bisk%2C+Y">Yonatan Bisk</a>, <a href="/search/cs?searchtype=author&query=Salakhutdinov%2C+R">Ruslan Salakhutdinov</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuanzhi Li</a>, <a href="/search/cs?searchtype=author&query=Mitchell%2C+T">Tom Mitchell</a>, <a href="/search/cs?searchtype=author&query=Prabhumoye%2C+S">Shrimai Prabhumoye</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.02412v2-abstract-short" style="display: inline;"> Pre-trained large language models (LLMs) capture procedural knowledge about the world. Recent work has leveraged LLM's ability to generate abstract plans to simplify challenging control tasks, either by action scoring, or action modeling (fine-tuning). However, the transformer architecture inherits several constraints that make it difficult for the LLM to directly serve as the agent: e.g. limited… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.02412v2-abstract-full').style.display = 'inline'; document.getElementById('2305.02412v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.02412v2-abstract-full" style="display: none;"> Pre-trained large language models (LLMs) capture procedural knowledge about the world. Recent work has leveraged LLM's ability to generate abstract plans to simplify challenging control tasks, either by action scoring, or action modeling (fine-tuning). However, the transformer architecture inherits several constraints that make it difficult for the LLM to directly serve as the agent: e.g. limited input lengths, fine-tuning inefficiency, bias from pre-training, and incompatibility with non-text environments. To maintain compatibility with a low-level trainable actor, we propose to instead use the knowledge in LLMs to simplify the control problem, rather than solving it. We propose the Plan, Eliminate, and Track (PET) framework. The Plan module translates a task description into a list of high-level sub-tasks. The Eliminate module masks out irrelevant objects and receptacles from the observation for the current sub-task. Finally, the Track module determines whether the agent has accomplished each sub-task. On the AlfWorld instruction following benchmark, the PET framework leads to a significant 15% improvement over SOTA for generalization to human goal specifications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.02412v2-abstract-full').style.display = 'none'; document.getElementById('2305.02412v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.13734">arXiv:2304.13734</a> <span> [<a href="https://arxiv.org/pdf/2304.13734">pdf</a>, <a href="https://arxiv.org/format/2304.13734">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> The Internal State of an LLM Knows When It's Lying </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Mitchell%2C+T">Tom Mitchell</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2304.13734v2-abstract-short" style="display: inline;"> While Large Language Models (LLMs) have shown exceptional performance in various tasks, one of their most prominent drawbacks is generating inaccurate or false information with a confident tone. In this paper, we provide evidence that the LLM's internal state can be used to reveal the truthfulness of statements. This includes both statements provided to the LLM, and statements that the LLM itself… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.13734v2-abstract-full').style.display = 'inline'; document.getElementById('2304.13734v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.13734v2-abstract-full" style="display: none;"> While Large Language Models (LLMs) have shown exceptional performance in various tasks, one of their most prominent drawbacks is generating inaccurate or false information with a confident tone. In this paper, we provide evidence that the LLM's internal state can be used to reveal the truthfulness of statements. This includes both statements provided to the LLM, and statements that the LLM itself generates. Our approach is to train a classifier that outputs the probability that a statement is truthful, based on the hidden layer activations of the LLM as it reads or generates the statement. Experiments demonstrate that given a set of test sentences, of which half are true and half false, our trained classifier achieves an average of 71\% to 83\% accuracy labeling which sentences are true versus false, depending on the LLM base model. Furthermore, we explore the relationship between our classifier's performance and approaches based on the probability assigned to the sentence by the LLM. We show that while LLM-assigned sentence probability is related to sentence truthfulness, this probability is also dependent on sentence length and the frequencies of words in the sentence, resulting in our trained classifier providing a more reliable approach to detecting truthfulness, highlighting its potential to enhance the reliability of LLM-generated content and its practical applicability in real-world scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.13734v2-abstract-full').style.display = 'none'; document.getElementById('2304.13734v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.04449">arXiv:2302.04449</a> <span> [<a href="https://arxiv.org/pdf/2302.04449">pdf</a>, <a href="https://arxiv.org/format/2302.04449">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+Y">Yue Wu</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+Y">Yewen Fan</a>, <a href="/search/cs?searchtype=author&query=Liang%2C+P+P">Paul Pu Liang</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yuanzhi Li</a>, <a href="/search/cs?searchtype=author&query=Mitchell%2C+T+M">Tom M. Mitchell</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2302.04449v4-abstract-short" style="display: inline;"> High sample complexity has long been a challenge for RL. On the other hand, humans learn to perform tasks not only from interaction or demonstrations, but also by reading unstructured text documents, e.g., instruction manuals. Instruction manuals and wiki pages are among the most abundant data that could inform agents of valuable features and policies or task-specific environmental dynamics and re… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.04449v4-abstract-full').style.display = 'inline'; document.getElementById('2302.04449v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.04449v4-abstract-full" style="display: none;"> High sample complexity has long been a challenge for RL. On the other hand, humans learn to perform tasks not only from interaction or demonstrations, but also by reading unstructured text documents, e.g., instruction manuals. Instruction manuals and wiki pages are among the most abundant data that could inform agents of valuable features and policies or task-specific environmental dynamics and reward structures. Therefore, we hypothesize that the ability to utilize human-written instruction manuals to assist learning policies for specific tasks should lead to a more efficient and better-performing agent. We propose the Read and Reward framework. Read and Reward speeds up RL algorithms on Atari games by reading manuals released by the Atari game developers. Our framework consists of a QA Extraction module that extracts and summarizes relevant information from the manual and a Reasoning module that evaluates object-agent interactions based on information from the manual. An auxiliary reward is then provided to a standard A2C RL agent, when interaction is detected. Experimentally, various RL algorithms obtain significant improvement in performance and training speed when assisted by our design. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.04449v4-abstract-full').style.display = 'none'; document.getElementById('2302.04449v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.15515">arXiv:2210.15515</a> <span> [<a href="https://arxiv.org/pdf/2210.15515">pdf</a>, <a href="https://arxiv.org/format/2210.15515">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Meta-Reinforcement Learning Using Model Parameters </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hartmann%2C+G">Gabriel Hartmann</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2210.15515v1-abstract-short" style="display: inline;"> In meta-reinforcement learning, an agent is trained in multiple different environments and attempts to learn a meta-policy that can efficiently adapt to a new environment. This paper presents RAMP, a Reinforcement learning Agent using Model Parameters that utilizes the idea that a neural network trained to predict environment dynamics encapsulates the environment information. RAMP is constructed i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.15515v1-abstract-full').style.display = 'inline'; document.getElementById('2210.15515v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.15515v1-abstract-full" style="display: none;"> In meta-reinforcement learning, an agent is trained in multiple different environments and attempts to learn a meta-policy that can efficiently adapt to a new environment. This paper presents RAMP, a Reinforcement learning Agent using Model Parameters that utilizes the idea that a neural network trained to predict environment dynamics encapsulates the environment information. RAMP is constructed in two phases: in the first phase, a multi-environment parameterized dynamic model is learned. In the second phase, the model parameters of the dynamic model are used as context for the multi-environment policy of the model-free reinforcement learning agent. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.15515v1-abstract-full').style.display = 'none'; document.getElementById('2210.15515v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.05034">arXiv:2201.05034</a> <span> [<a href="https://arxiv.org/pdf/2201.05034">pdf</a>, <a href="https://arxiv.org/format/2201.05034">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Criticality-Based Varying Step-Number Algorithm for Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Spielberg%2C+Y">Yitzhak Spielberg</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2201.05034v1-abstract-short" style="display: inline;"> In the context of reinforcement learning we introduce the concept of criticality of a state, which indicates the extent to which the choice of action in that particular state influences the expected return. That is, a state in which the choice of action is more likely to influence the final outcome is considered as more critical than a state in which it is less likely to influence the final outcom… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.05034v1-abstract-full').style.display = 'inline'; document.getElementById('2201.05034v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.05034v1-abstract-full" style="display: none;"> In the context of reinforcement learning we introduce the concept of criticality of a state, which indicates the extent to which the choice of action in that particular state influences the expected return. That is, a state in which the choice of action is more likely to influence the final outcome is considered as more critical than a state in which it is less likely to influence the final outcome. We formulate a criticality-based varying step number algorithm (CVS) - a flexible step number algorithm that utilizes the criticality function provided by a human, or learned directly from the environment. We test it in three different domains including the Atari Pong environment, Road-Tree environment, and Shooter environment. We demonstrate that CVS is able to outperform popular learning algorithms such as Deep Q-Learning and Monte Carlo. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.05034v1-abstract-full').style.display = 'none'; document.getElementById('2201.05034v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: text overlap with arXiv:1810.07254</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> International Journal on Artificial Intelligence Tools, vol. 30, 2021 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.04633">arXiv:2201.04633</a> <span> [<a href="https://arxiv.org/pdf/2201.04633">pdf</a>, <a href="https://arxiv.org/format/2201.04633">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Revelation of Task Difficulty in AI-aided Education </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Spielberg%2C+Y">Yitzhak Spielberg</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2201.04633v1-abstract-short" style="display: inline;"> When a student is asked to perform a given task, her subjective estimate of the difficulty of that task has a strong influence on her performance. There exists a rich literature on the impact of perceived task difficulty on performance and motivation. Yet, there is another topic that is closely related to the subject of the influence of perceived task difficulty that did not receive any attention… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.04633v1-abstract-full').style.display = 'inline'; document.getElementById('2201.04633v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.04633v1-abstract-full" style="display: none;"> When a student is asked to perform a given task, her subjective estimate of the difficulty of that task has a strong influence on her performance. There exists a rich literature on the impact of perceived task difficulty on performance and motivation. Yet, there is another topic that is closely related to the subject of the influence of perceived task difficulty that did not receive any attention in previous research - the influence of revealing the true difficulty of a task to the student. This paper investigates the impact of revealing the task difficulty on the student's performance, motivation, self-efficacy and subjective task value via an experiment in which workers are asked to solve matchstick riddles. Furthermore, we discuss how the experiment results might be relevant for AI-aided education. Specifically, we elaborate on the question of how a student's learning experience might be improved by supporting her with two types of AI systems: an AI system that predicts task difficulty and an AI system that determines when task difficulty should be revealed and when not. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.04633v1-abstract-full').style.display = 'none'; document.getElementById('2201.04633v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.04632">arXiv:2201.04632</a> <span> [<a href="https://arxiv.org/pdf/2201.04632">pdf</a>, <a href="https://arxiv.org/format/2201.04632">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> The Concept of Criticality in AI Safety </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Spielberg%2C+Y">Yitzhak Spielberg</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2201.04632v2-abstract-short" style="display: inline;"> When AI agents don't align their actions with human values they may cause serious harm. One way to solve the value alignment problem is by including a human operator who monitors all of the agent's actions. Despite the fact, that this solution guarantees maximal safety, it is very inefficient, since it requires the human operator to dedicate all of his attention to the agent. In this paper, we pro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.04632v2-abstract-full').style.display = 'inline'; document.getElementById('2201.04632v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.04632v2-abstract-full" style="display: none;"> When AI agents don't align their actions with human values they may cause serious harm. One way to solve the value alignment problem is by including a human operator who monitors all of the agent's actions. Despite the fact, that this solution guarantees maximal safety, it is very inefficient, since it requires the human operator to dedicate all of his attention to the agent. In this paper, we propose a much more efficient solution that allows an operator to be engaged in other activities without neglecting his monitoring task. In our approach the AI agent requests permission from the operator only for critical actions, that is, potentially harmful actions. We introduce the concept of critical actions with respect to AI safety and discuss how to build a model that measures action criticality. We also discuss how the operator's feedback could be used to make the agent smarter. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.04632v2-abstract-full').style.display = 'none'; document.getElementById('2201.04632v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.05486">arXiv:2109.05486</a> <span> [<a href="https://arxiv.org/pdf/2109.05486">pdf</a>, <a href="https://arxiv.org/format/2109.05486">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> A Socially Aware Reinforcement Learning Agent for The Single Track Road Problem </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shapira%2C+I">Ido Shapira</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2109.05486v3-abstract-short" style="display: inline;"> We present the single track road problem. In this problem two agents face each-other at opposite positions of a road that can only have one agent pass at a time. We focus on the scenario in which one agent is human, while the other is an autonomous agent. We run experiments with human subjects in a simple grid domain, which simulates the single track road problem. We show that when data is limited… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.05486v3-abstract-full').style.display = 'inline'; document.getElementById('2109.05486v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.05486v3-abstract-full" style="display: none;"> We present the single track road problem. In this problem two agents face each-other at opposite positions of a road that can only have one agent pass at a time. We focus on the scenario in which one agent is human, while the other is an autonomous agent. We run experiments with human subjects in a simple grid domain, which simulates the single track road problem. We show that when data is limited, building an accurate human model is very challenging, and that a reinforcement learning agent, which is based on this data, does not perform well in practice. However, we show that an agent that tries to maximize a linear combination of the human's utility and its own utility, achieves a high score, and significantly outperforms other baselines, including an agent that tries to maximize only its own utility. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.05486v3-abstract-full').style.display = 'none'; document.getElementById('2109.05486v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.05455">arXiv:2109.05455</a> <span> [<a href="https://arxiv.org/pdf/2109.05455">pdf</a>, <a href="https://arxiv.org/format/2109.05455">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/ACCESS.2022.3215984">10.1109/ACCESS.2022.3215984 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Competitive Driving of Autonomous Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hartmann%2C+G">Gabriel Hartmann</a>, <a href="/search/cs?searchtype=author&query=Shiller%2C+Z">Zvi Shiller</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2109.05455v2-abstract-short" style="display: inline;"> This paper describes Ariel Team's autonomous racing controller for the Indy Autonomous Challenge (IAC) simulation race. IAC is the first multi-vehicle autonomous head-to-head competition, reaching speeds of 300 km/h along an oval track, modeled after the Indianapolis Motor Speedway (IMS). Our racing controller attempts to maximize progress along the track while avoiding collisions with opponent ve… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.05455v2-abstract-full').style.display = 'inline'; document.getElementById('2109.05455v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.05455v2-abstract-full" style="display: none;"> This paper describes Ariel Team's autonomous racing controller for the Indy Autonomous Challenge (IAC) simulation race. IAC is the first multi-vehicle autonomous head-to-head competition, reaching speeds of 300 km/h along an oval track, modeled after the Indianapolis Motor Speedway (IMS). Our racing controller attempts to maximize progress along the track while avoiding collisions with opponent vehicles and obeying the race rules. To this end, the racing controller first computes a race line offline. Then, it repeatedly computes online a small set of dynamically feasible maneuver candidates, each tested for collision with the opponent vehicles. Finally, it selects the maneuver that maximizes progress along the track, taking into account the race line. The maneuver candidates, as well as the predicted trajectories of the opponent vehicles, are approximated using a point mass model. Despite the simplicity of this racing controller, it managed to drive competitively and with no collision with any of the opponent vehicles in the IAC final simulation race. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.05455v2-abstract-full').style.display = 'none'; document.getElementById('2109.05455v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Access, Volume: 10, Publication Date: 2022, On Pages: 111772-111783 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2105.12500">arXiv:2105.12500</a> <span> [<a href="https://arxiv.org/pdf/2105.12500">pdf</a>, <a href="https://arxiv.org/format/2105.12500">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Explaining Ridesharing: Selection of Explanations for Increasing User Satisfaction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zar%2C+D">David Zar</a>, <a href="/search/cs?searchtype=author&query=Hazon%2C+N">Noam Hazon</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2105.12500v1-abstract-short" style="display: inline;"> Transportation services play a crucial part in the development of modern smart cities. In particular, on-demand ridesharing services, which group together passengers with similar itineraries, are already operating in several metropolitan areas. These services can be of significant social and environmental benefit, by reducing travel costs, road congestion and CO2 emissions. Unfortunately, despit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.12500v1-abstract-full').style.display = 'inline'; document.getElementById('2105.12500v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2105.12500v1-abstract-full" style="display: none;"> Transportation services play a crucial part in the development of modern smart cities. In particular, on-demand ridesharing services, which group together passengers with similar itineraries, are already operating in several metropolitan areas. These services can be of significant social and environmental benefit, by reducing travel costs, road congestion and CO2 emissions. Unfortunately, despite their advantages, not many people opt to use these ridesharing services. We believe that increasing the user satisfaction from the service will cause more people to utilize it, which, in turn, will improve the quality of the service, such as the waiting time, cost, travel time, and service availability. One possible way for increasing user satisfaction is by providing appropriate explanations comparing the alternative modes of transportation, such as a private taxi ride and public transportation. For example, a passenger may be more satisfied from a shared-ride if she is told that a private taxi ride would have cost her 50% more. Therefore, the problem is to develop an agent that provides explanations that will increase the user satisfaction. We model our environment as a signaling game and show that a rational agent, which follows the perfect Bayesian equilibrium, must reveal all of the information regarding the possible alternatives to the passenger. In addition, we develop a machine learning based agent that, when given a shared-ride along with its possible alternatives, selects the explanations that are most likely to increase user satisfaction. Using feedback from humans we show that our machine learning based agent outperforms the rational agent and an agent that randomly chooses explanations, in terms of user satisfaction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.12500v1-abstract-full').style.display = 'none'; document.getElementById('2105.12500v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 May, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">19 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.10022">arXiv:2006.10022</a> <span> [<a href="https://arxiv.org/pdf/2006.10022">pdf</a>, <a href="https://arxiv.org/format/2006.10022">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Conversational Neuro-Symbolic Commonsense Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Arabshahi%2C+F">Forough Arabshahi</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+J">Jennifer Lee</a>, <a href="/search/cs?searchtype=author&query=Gawarecki%2C+M">Mikayla Gawarecki</a>, <a href="/search/cs?searchtype=author&query=Mazaitis%2C+K">Kathryn Mazaitis</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Mitchell%2C+T">Tom Mitchell</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2006.10022v3-abstract-short" style="display: inline;"> In order for conversational AI systems to hold more natural and broad-ranging conversations, they will require much more commonsense, including the ability to identify unstated presumptions of their conversational partners. For example, in the command "If it snows at night then wake me up early because I don't want to be late for work" the speaker relies on commonsense reasoning of the listener to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.10022v3-abstract-full').style.display = 'inline'; document.getElementById('2006.10022v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.10022v3-abstract-full" style="display: none;"> In order for conversational AI systems to hold more natural and broad-ranging conversations, they will require much more commonsense, including the ability to identify unstated presumptions of their conversational partners. For example, in the command "If it snows at night then wake me up early because I don't want to be late for work" the speaker relies on commonsense reasoning of the listener to infer the implicit presumption that they wish to be woken only if it snows enough to cause traffic slowdowns. We consider here the problem of understanding such imprecisely stated natural language commands given in the form of "if-(state), then-(action), because-(goal)" statements. More precisely, we consider the problem of identifying the unstated presumptions of the speaker that allow the requested action to achieve the desired goal from the given state (perhaps elaborated by making the implicit presumptions explicit). We release a benchmark data set for this task, collected from humans and annotated with commonsense presumptions. We present a neuro-symbolic theorem prover that extracts multi-hop reasoning chains, and apply it to this problem. Furthermore, to accommodate the reality that current AI commonsense systems lack full coverage, we also present an interactive conversational framework built on our neuro-symbolic system, that conversationally evokes commonsense knowledge from humans to complete its reasoning chains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.10022v3-abstract-full').style.display = 'none'; document.getElementById('2006.10022v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Appearing in the 35th AAAI international Conference on Artificial Intelligence, 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1912.00698">arXiv:1912.00698</a> <span> [<a href="https://arxiv.org/pdf/1912.00698">pdf</a>, <a href="https://arxiv.org/format/1912.00698">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Fiction Sentence Expansion and Enhancement via Focused Objective and Novelty Curve Sampling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Safovich%2C+Y">Yuri Safovich</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1912.00698v3-abstract-short" style="display: inline;"> We describe the task of sentence expansion and enhancement, in which a sentence provided by a human is expanded in some creative way. The expansion should be understandable, believably grammatical, and optimally meaning-preserving. Sentence expansion and enhancement may serve as an authoring tool, or integrate in dynamic media, conversational agents, or variegated advertising. We implement a neu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.00698v3-abstract-full').style.display = 'inline'; document.getElementById('1912.00698v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.00698v3-abstract-full" style="display: none;"> We describe the task of sentence expansion and enhancement, in which a sentence provided by a human is expanded in some creative way. The expansion should be understandable, believably grammatical, and optimally meaning-preserving. Sentence expansion and enhancement may serve as an authoring tool, or integrate in dynamic media, conversational agents, or variegated advertising. We implement a neural sentence expander trained on sentence compressions generated from a corpus of modern fiction. We modify an MLE objective to support the task by focusing on new words, and decode at test time with controlled curve-like novelty sampling. We run our sentence expander on sentences provided by human subjects and have humans evaluate these expansions. We show that, although the generation methods are inferior to professional human writers, they are comparable to, and as well liked as, our subjects' original input sentences, and preferred over baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.00698v3-abstract-full').style.display = 'none'; document.getElementById('1912.00698v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at ICTAI 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1910.04404">arXiv:1910.04404</a> <span> [<a href="https://arxiv.org/pdf/1910.04404">pdf</a>, <a href="https://arxiv.org/format/1910.04404">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1609/aaai.v34i09.7077">10.1609/aaai.v34i09.7077 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> AI for Explaining Decisions in Multi-Agent Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kraus%2C+S">Sarit Kraus</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Fiosina%2C+J">Jelena Fiosina</a>, <a href="/search/cs?searchtype=author&query=Greve%2C+M">Maike Greve</a>, <a href="/search/cs?searchtype=author&query=Hazon%2C+N">Noam Hazon</a>, <a href="/search/cs?searchtype=author&query=Kolbe%2C+L">Lutz Kolbe</a>, <a href="/search/cs?searchtype=author&query=Lembcke%2C+T">Tim-Benjamin Lembcke</a>, <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+J+P">J枚rg P. M眉ller</a>, <a href="/search/cs?searchtype=author&query=Schleibaum%2C+S">S枚ren Schleibaum</a>, <a href="/search/cs?searchtype=author&query=Vollrath%2C+M">Mark Vollrath</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1910.04404v2-abstract-short" style="display: inline;"> Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not know the systems' goals since they may depend on other agents' preferences. In such situations, explanations should aim to increase user satisfaction, taking int… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1910.04404v2-abstract-full').style.display = 'inline'; document.getElementById('1910.04404v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1910.04404v2-abstract-full" style="display: none;"> Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not know the systems' goals since they may depend on other agents' preferences. In such situations, explanations should aim to increase user satisfaction, taking into account the system's decision, the user's and the other agents' preferences, the environment settings and properties such as fairness, envy and privacy. Generating explanations that will increase user satisfaction is very challenging; to this end, we propose a new research direction: xMASE. We then review the state of the art and discuss research directions towards efficient methodologies and algorithms for generating explanations that will increase users' satisfaction from AI system's decisions in multi-agent environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1910.04404v2-abstract-full').style.display = 'none'; document.getElementById('1910.04404v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 October, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 October, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper has been submitted to the Blue Sky Track of the AAAI 2020 conference. At the time of submission, it is under review. The tentative notification date will be November 10, 2019. Current version: Name of first author had been added in metadata</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1909.09156">arXiv:1909.09156</a> <span> [<a href="https://arxiv.org/pdf/1909.09156">pdf</a>, <a href="https://arxiv.org/format/1909.09156">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Learning to Conceal: A Deep Learning Based Method for Preserving Privacy and Avoiding Prejudice </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hanukoglu%2C+M">Moshe Hanukoglu</a>, <a href="/search/cs?searchtype=author&query=Goldberg%2C+N">Nissan Goldberg</a>, <a href="/search/cs?searchtype=author&query=Rovshitz%2C+A">Aviv Rovshitz</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1909.09156v1-abstract-short" style="display: inline;"> In this paper, we introduce a learning model able to conceals personal information (e.g. gender, age, ethnicity, etc.) from an image, while maintaining any additional information present in the image (e.g. smile, hair-style, brightness). Our trained model is not provided the information that it is concealing, and does not try learning it either. Namely, we created a variational autoencoder (VAE) m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.09156v1-abstract-full').style.display = 'inline'; document.getElementById('1909.09156v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1909.09156v1-abstract-full" style="display: none;"> In this paper, we introduce a learning model able to conceals personal information (e.g. gender, age, ethnicity, etc.) from an image, while maintaining any additional information present in the image (e.g. smile, hair-style, brightness). Our trained model is not provided the information that it is concealing, and does not try learning it either. Namely, we created a variational autoencoder (VAE) model that is trained on a dataset including labels of the information one would like to conceal (e.g. gender, ethnicity, age). These labels are directly added to the VAE's sampled latent vector. Due to the limited number of neurons in the latent vector and its appended noise, the VAE avoids learning any relation between the given images and the given labels, as those are given directly. Therefore, the encoded image lacks any of the information one wishes to conceal. The encoding may be decoded back into an image according to any provided properties (e.g. a 40 year old woman). The proposed architecture can be used as a mean for privacy preserving and can serve as an input to systems, which will become unbiased and not suffer from prejudice. We believe that privacy and discrimination are two of the most important aspects in which the community should try and develop methods to prevent misuse of technological advances. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.09156v1-abstract-full').style.display = 'none'; document.getElementById('1909.09156v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 September, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1909.05725">arXiv:1909.05725</a> <span> [<a href="https://arxiv.org/pdf/1909.05725">pdf</a>, <a href="https://arxiv.org/format/1909.05725">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.15346/hc.v6i1.7">10.15346/hc.v6i1.7 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> InstructableCrowd: Creating IF-THEN Rules for Smartphones via Conversations with the Crowd </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+T+%27">Ting-Hao 'Kenneth' Huang</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Romero%2C+O+J">Oscar J. Romero</a>, <a href="/search/cs?searchtype=author&query=Bigham%2C+J+P">Jeffrey P. Bigham</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1909.05725v1-abstract-short" style="display: inline;"> Natural language interfaces have become a common part of modern digital life. Chatbots utilize text-based conversations to communicate with users; personal assistants on smartphones such as Google Assistant take direct speech commands from their users; and speech-controlled devices such as Amazon Echo use voice as their only input mode. In this paper, we introduce InstructableCrowd, a crowd-powere… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.05725v1-abstract-full').style.display = 'inline'; document.getElementById('1909.05725v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1909.05725v1-abstract-full" style="display: none;"> Natural language interfaces have become a common part of modern digital life. Chatbots utilize text-based conversations to communicate with users; personal assistants on smartphones such as Google Assistant take direct speech commands from their users; and speech-controlled devices such as Amazon Echo use voice as their only input mode. In this paper, we introduce InstructableCrowd, a crowd-powered system that allows users to program their devices via conversation. The user verbally expresses a problem to the system, in which a group of crowd workers collectively respond and program relevant multi-part IF-THEN rules to help the user. The IF-THEN rules generated by InstructableCrowd connect relevant sensor combinations (e.g., location, weather, device acceleration, etc.) to useful effectors (e.g., text messages, device alarms, etc.). Our study showed that non-programmers can use the conversational interface of InstructableCrowd to create IF-THEN rules that have similar quality compared with the rules created manually. InstructableCrowd generally illustrates how users may converse with their devices, not only to trigger simple voice commands, but also to personalize their increasingly powerful and complicated devices. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.05725v1-abstract-full').style.display = 'none'; document.getElementById('1909.05725v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 September, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published at Human Computation (2019) 6:1:113-146</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Human Computation (2019) 6:1:113-146 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1909.04713">arXiv:1909.04713</a> <span> [<a href="https://arxiv.org/pdf/1909.04713">pdf</a>, <a href="https://arxiv.org/format/1909.04713">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Fair Sharing: The Shapley Value for Ride-Sharing and Routing Games </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Levinger%2C+C">Chaya Levinger</a>, <a href="/search/cs?searchtype=author&query=Hazon%2C+N">Noam Hazon</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1909.04713v1-abstract-short" style="display: inline;"> Ride-sharing services are gaining popularity and are crucial for a sustainable environment. A special case in which such services are most applicable, is the last mile variant. In this variant it is assumed that all the passengers are positioned at the same origin location (e.g. an airport), and each have a different destination. One of the major issues in a shared ride is fairly splitting of the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.04713v1-abstract-full').style.display = 'inline'; document.getElementById('1909.04713v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1909.04713v1-abstract-full" style="display: none;"> Ride-sharing services are gaining popularity and are crucial for a sustainable environment. A special case in which such services are most applicable, is the last mile variant. In this variant it is assumed that all the passengers are positioned at the same origin location (e.g. an airport), and each have a different destination. One of the major issues in a shared ride is fairly splitting of the ride cost among the passengers. In this paper we use the Shapley value, which is one of the most significant solution concepts in cooperative game theory, for fairly splitting the cost of a shared ride. We consider two scenarios. In the first scenario there exists a fixed priority order in which the passengers are dropped-off (e.g. elderly, injured etc.), and we show a method for efficient computation of the Shapley value in this setting. Our results are also applicable for efficient computation of the Shapley value in routing games. In the second scenario there is no predetermined priority order. We show that the Shapley value cannot be efficiently computed in this setting. However, extensive simulations reveal that our approach for the first scenario can serve as an excellent proxy for the second scenario, outperforming other known proxies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.04713v1-abstract-full').style.display = 'none'; document.getElementById('1909.04713v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 September, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1902.09093">arXiv:1902.09093</a> <span> [<a href="https://arxiv.org/pdf/1902.09093">pdf</a>, <a href="https://arxiv.org/format/1902.09093">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Multi-Relational Question Answering from Narratives: Machine Reading and Reasoning in Simulated Worlds </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Labutov%2C+I">Igor Labutov</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+B">Bishan Yang</a>, <a href="/search/cs?searchtype=author&query=Prakash%2C+A">Anusha Prakash</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1902.09093v1-abstract-short" style="display: inline;"> Question Answering (QA), as a research field, has primarily focused on either knowledge bases (KBs) or free text as a source of knowledge. These two sources have historically shaped the kinds of questions that are asked over these sources, and the methods developed to answer them. In this work, we look towards a practical use-case of QA over user-instructed knowledge that uniquely combines element… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.09093v1-abstract-full').style.display = 'inline'; document.getElementById('1902.09093v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1902.09093v1-abstract-full" style="display: none;"> Question Answering (QA), as a research field, has primarily focused on either knowledge bases (KBs) or free text as a source of knowledge. These two sources have historically shaped the kinds of questions that are asked over these sources, and the methods developed to answer them. In this work, we look towards a practical use-case of QA over user-instructed knowledge that uniquely combines elements of both structured QA over knowledge bases, and unstructured QA over narrative, introducing the task of multi-relational QA over personal narrative. As a first step towards this goal, we make three key contributions: (i) we generate and release TextWorldsQA, a set of five diverse datasets, where each dataset contains dynamic narrative that describes entities and relations in a simulated world, paired with variably compositional questions over that knowledge, (ii) we perform a thorough evaluation and analysis of several state-of-the-art QA models and their variants at this task, and (iii) we release a lightweight Python-based framework we call TextWorlds for easily generating arbitrary additional worlds and narrative, with the goal of allowing the community to create and share a growing collection of diverse worlds as a test-bed for this task. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.09093v1-abstract-full').style.display = 'none'; document.getElementById('1902.09093v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 February, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">published at ACL 2018</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> ACL 2018 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1811.11615">arXiv:1811.11615</a> <span> [<a href="https://arxiv.org/pdf/1811.11615">pdf</a>, <a href="https://arxiv.org/format/1811.11615">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Deep Reinforcement Learning for Time Optimal Velocity Control using Prior Knowledge </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hartmann%2C+G">Gabriel Hartmann</a>, <a href="/search/cs?searchtype=author&query=Shiller%2C+Z">Zvi Shiller</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1811.11615v3-abstract-short" style="display: inline;"> Autonomous navigation has recently gained great interest in the field of reinforcement learning. However, little attention was given to the time optimal velocity control problem, i.e. controlling a vehicle such that it travels at the maximal speed without becoming dynamically unstable (roll-over or sliding). Time optimal velocity control can be solved numerically using existing methods that are… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.11615v3-abstract-full').style.display = 'inline'; document.getElementById('1811.11615v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1811.11615v3-abstract-full" style="display: none;"> Autonomous navigation has recently gained great interest in the field of reinforcement learning. However, little attention was given to the time optimal velocity control problem, i.e. controlling a vehicle such that it travels at the maximal speed without becoming dynamically unstable (roll-over or sliding). Time optimal velocity control can be solved numerically using existing methods that are based on optimal control and vehicle dynamics. In this paper, we use deep reinforcement learning to generate the time optimal velocity control. Furthermore, we use the numerical solution to further improve the performance of the reinforcement learner. It is shown that the reinforcement learner outperforms the numerically derived solution, and that the hybrid approach (combining learning with the numerical solution) speeds up the training process. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.11615v3-abstract-full').style.display = 'none'; document.getElementById('1811.11615v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 July, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 November, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1810.07254">arXiv:1810.07254</a> <span> [<a href="https://arxiv.org/pdf/1810.07254">pdf</a>, <a href="https://arxiv.org/format/1810.07254">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> The Concept of Criticality in Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Spielberg%2C+Y">Yitzhak Spielberg</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1810.07254v1-abstract-short" style="display: inline;"> Reinforcement learning methods carry a well known bias-variance trade-off in n-step algorithms for optimal control. Unfortunately, this has rarely been addressed in current research. This trade-off principle holds independent of the choice of the algorithm, such as n-step SARSA, n-step Expected SARSA or n-step Tree backup. A small n results in a large bias, while a large n leads to large variance.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.07254v1-abstract-full').style.display = 'inline'; document.getElementById('1810.07254v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1810.07254v1-abstract-full" style="display: none;"> Reinforcement learning methods carry a well known bias-variance trade-off in n-step algorithms for optimal control. Unfortunately, this has rarely been addressed in current research. This trade-off principle holds independent of the choice of the algorithm, such as n-step SARSA, n-step Expected SARSA or n-step Tree backup. A small n results in a large bias, while a large n leads to large variance. The literature offers no straightforward recipe for the best choice of this value. While currently all n-step algorithms use a fixed value of n over the state space we extend the framework of n-step updates by allowing each state to have its specific n. We propose a solution to this problem within the context of human aided reinforcement learning. Our approach is based on the observation that a human can learn more efficiently if she receives input regarding the criticality of a given state and thus the amount of attention she needs to invest into the learning in that state. This observation is related to the idea that each state of the MDP has a certain measure of criticality which indicates how much the choice of the action in that state influences the return. In our algorithm the RL agent utilizes the criticality measure, a function provided by a human trainer, in order to locally choose the best stepnumber n for the update of the Q function. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.07254v1-abstract-full').style.display = 'none'; document.getElementById('1810.07254v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 October, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1807.00376">arXiv:1807.00376</a> <span> [<a href="https://arxiv.org/pdf/1807.00376">pdf</a>, <a href="https://arxiv.org/format/1807.00376">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1016/j.future.2020.05.028">10.1016/j.future.2020.05.028 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Human Satisfaction as the Ultimate Goal in Ridesharing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Levinger%2C+C">Chaya Levinger</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Hazon%2C+N">Noam Hazon</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1807.00376v1-abstract-short" style="display: inline;"> Transportation services play a crucial part in the development of modern smart cities. In particular, on-demand ridesharing services, which group together passengers with similar itineraries, are already operating in several metropolitan areas. These services can be of significant social and environmental benefit, by reducing travel costs, road congestion and co2 emissions. The deployment of auton… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1807.00376v1-abstract-full').style.display = 'inline'; document.getElementById('1807.00376v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1807.00376v1-abstract-full" style="display: none;"> Transportation services play a crucial part in the development of modern smart cities. In particular, on-demand ridesharing services, which group together passengers with similar itineraries, are already operating in several metropolitan areas. These services can be of significant social and environmental benefit, by reducing travel costs, road congestion and co2 emissions. The deployment of autonomous cars in the near future will surely change the way people are traveling. It is even more promising for a ridesharing service, since it will be easier and cheaper for a company to handle a fleet of autonomous cars that can serve the demands of different passengers. We argue that user satisfaction should be the main objective when trying to find the best assignment of passengers to vehicles and the determination of their routes. Moreover, the model of user satisfaction should be rich enough to capture the traveling distance, cost, and other factors as well. We show that it is more important to capture a rich model of human satisfaction than peruse an optimal performance. That is, we developed a practical algorithm for assigning passengers to vehicles, which outperforms assignment algorithms that are optimal, but use a simpler satisfaction model. To the best of our knowledge, this is the first paper to exclusively concentrate on a rich and realistic function of user satisfaction as the objective, which is (arguably) the most important aspect to consider for achieving a widespread adaption of ridesharing services. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1807.00376v1-abstract-full').style.display = 'none'; document.getElementById('1807.00376v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 July, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1803.09237">arXiv:1803.09237</a> <span> [<a href="https://arxiv.org/pdf/1803.09237">pdf</a>, <a href="https://arxiv.org/format/1803.09237">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Goldbach's Function Approximation Using Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Stekel%2C+A">Avigail Stekel</a>, <a href="/search/cs?searchtype=author&query=Chkroun%2C+M">Merav Chkroun</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1803.09237v1-abstract-short" style="display: inline;"> Goldbach conjecture is one of the most famous open mathematical problems. It states that every even number, bigger than two, can be presented as a sum of 2 prime numbers. % In this work we present a deep learning based model that predicts the number of Goldbach partitions for a given even number. Surprisingly, our model outperforms all state-of-the-art analytically derived estimations for the numb… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1803.09237v1-abstract-full').style.display = 'inline'; document.getElementById('1803.09237v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1803.09237v1-abstract-full" style="display: none;"> Goldbach conjecture is one of the most famous open mathematical problems. It states that every even number, bigger than two, can be presented as a sum of 2 prime numbers. % In this work we present a deep learning based model that predicts the number of Goldbach partitions for a given even number. Surprisingly, our model outperforms all state-of-the-art analytically derived estimations for the number of couples, while not requiring prime factorization of the given number. We believe that building a model that can accurately predict the number of couples brings us one step closer to solving one of the world most famous open problems. To the best of our knowledge, this is the first attempt to consider machine learning based data-driven methods to approximate open mathematical problems in the field of number theory, and hope that this work will encourage such attempts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1803.09237v1-abstract-full').style.display = 'none'; document.getElementById('1803.09237v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 March, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1708.03044">arXiv:1708.03044</a> <span> [<a href="https://arxiv.org/pdf/1708.03044">pdf</a>, <a href="https://arxiv.org/format/1708.03044">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> "Is there anything else I can help you with?": Challenges in Deploying an On-Demand Crowd-Powered Conversational Agent </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+T+K">Ting-Hao Kenneth Huang</a>, <a href="/search/cs?searchtype=author&query=Lasecki%2C+W+S">Walter S. Lasecki</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Bigham%2C+J+P">Jeffrey P. Bigham</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1708.03044v1-abstract-short" style="display: inline;"> Intelligent conversational assistants, such as Apple's Siri, Microsoft's Cortana, and Amazon's Echo, have quickly become a part of our digital life. However, these assistants have major limitations, which prevents users from conversing with them as they would with human dialog partners. This limits our ability to observe how users really want to interact with the underlying system. To address this… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1708.03044v1-abstract-full').style.display = 'inline'; document.getElementById('1708.03044v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1708.03044v1-abstract-full" style="display: none;"> Intelligent conversational assistants, such as Apple's Siri, Microsoft's Cortana, and Amazon's Echo, have quickly become a part of our digital life. However, these assistants have major limitations, which prevents users from conversing with them as they would with human dialog partners. This limits our ability to observe how users really want to interact with the underlying system. To address this problem, we developed a crowd-powered conversational assistant, Chorus, and deployed it to see how users and workers would interact together when mediated by the system. Chorus sophisticatedly converses with end users over time by recruiting workers on demand, which in turn decide what might be the best response for each user sentence. Up to the first month of our deployment, 59 users have held conversations with Chorus during 320 conversational sessions. In this paper, we present an account of Chorus' deployment, with a focus on four challenges: (i) identifying when conversations are over, (ii) malicious users and workers, (iii) on-demand recruiting, and (iv) settings in which consensus is not enough. Our observations could assist the deployment of crowd-powered conversation systems and crowd-powered systems in general. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1708.03044v1-abstract-full').style.display = 'none'; document.getElementById('1708.03044v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 August, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2017. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages. In Proceedings of Conference on Human Computation & Crowdsourcing (HCOMP 2016), 2016, Austin, TX, USA</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1601.05140">arXiv:1601.05140</a> <span> [<a href="https://arxiv.org/pdf/1601.05140">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Analysis, Statistics and Probability">physics.data-an</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Physics and Society">physics.soc-ph</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/MC.2016.183">10.1109/MC.2016.183 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> The DARPA Twitter Bot Challenge </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Subrahmanian%2C+V+S">V. S. Subrahmanian</a>, <a href="/search/cs?searchtype=author&query=Azaria%2C+A">Amos Azaria</a>, <a href="/search/cs?searchtype=author&query=Durst%2C+S">Skylar Durst</a>, <a href="/search/cs?searchtype=author&query=Kagan%2C+V">Vadim Kagan</a>, <a href="/search/cs?searchtype=author&query=Galstyan%2C+A">Aram Galstyan</a>, <a href="/search/cs?searchtype=author&query=Lerman%2C+K">Kristina Lerman</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+L">Linhong Zhu</a>, <a href="/search/cs?searchtype=author&query=Ferrara%2C+E">Emilio Ferrara</a>, <a href="/search/cs?searchtype=author&query=Flammini%2C+A">Alessandro Flammini</a>, <a href="/search/cs?searchtype=author&query=Menczer%2C+F">Filippo Menczer</a>, <a href="/search/cs?searchtype=author&query=Stevens%2C+A">Andrew Stevens</a>, <a href="/search/cs?searchtype=author&query=Dekhtyar%2C+A">Alexander Dekhtyar</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+S">Shuyang Gao</a>, <a href="/search/cs?searchtype=author&query=Hogg%2C+T">Tad Hogg</a>, <a href="/search/cs?searchtype=author&query=Kooti%2C+F">Farshad Kooti</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Y">Yan Liu</a>, <a href="/search/cs?searchtype=author&query=Varol%2C+O">Onur Varol</a>, <a href="/search/cs?searchtype=author&query=Shiralkar%2C+P">Prashant Shiralkar</a>, <a href="/search/cs?searchtype=author&query=Vydiswaran%2C+V">Vinod Vydiswaran</a>, <a href="/search/cs?searchtype=author&query=Mei%2C+Q">Qiaozhu Mei</a>, <a href="/search/cs?searchtype=author&query=Hwang%2C+T">Tim Hwang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1601.05140v2-abstract-short" style="display: inline;"> A number of organizations ranging from terrorist groups such as ISIS to politicians and nation states reportedly conduct explicit campaigns to influence opinion on social media, posing a risk to democratic processes. There is thus a growing need to identify and eliminate "influence bots" - realistic, automated identities that illicitly shape discussion on sites like Twitter and Facebook - before t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1601.05140v2-abstract-full').style.display = 'inline'; document.getElementById('1601.05140v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1601.05140v2-abstract-full" style="display: none;"> A number of organizations ranging from terrorist groups such as ISIS to politicians and nation states reportedly conduct explicit campaigns to influence opinion on social media, posing a risk to democratic processes. There is thus a growing need to identify and eliminate "influence bots" - realistic, automated identities that illicitly shape discussion on sites like Twitter and Facebook - before they get too influential. Spurred by such events, DARPA held a 4-week competition in February/March 2015 in which multiple teams supported by the DARPA Social Media in Strategic Communications program competed to identify a set of previously identified "influence bots" serving as ground truth on a specific topic within Twitter. Past work regarding influence bots often has difficulty supporting claims about accuracy, since there is limited ground truth (though some exceptions do exist [3,7]). However, with the exception of [3], no past work has looked specifically at identifying influence bots on a specific topic. This paper describes the DARPA Challenge and describes the methods used by the three top-ranked teams. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1601.05140v2-abstract-full').style.display = 'none'; document.getElementById('1601.05140v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 April, 2016; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 January, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2016. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">IEEE Computer Magazine, in press</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Computer 49 (6), 38-46. IEEE, 2016 </p> </li> </ol> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository