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 1–14 of 14 results for author: <span class="mathjax">Szot, 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=Szot%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="Szot, 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=Szot%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="Szot, 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/2410.02751">arXiv:2410.02751</a> <span> [<a href="https://arxiv.org/pdf/2410.02751">pdf</a>, <a href="https://arxiv.org/format/2410.02751">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"> ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Elawady%2C+A">Ahmad Elawady</a>, <a href="/search/cs?searchtype=author&query=Chhablani%2C+G">Gunjan Chhablani</a>, <a href="/search/cs?searchtype=author&query=Ramrakhya%2C+R">Ram Ramrakhya</a>, <a href="/search/cs?searchtype=author&query=Yadav%2C+K">Karmesh Yadav</a>, <a href="/search/cs?searchtype=author&query=Batra%2C+D">Dhruv Batra</a>, <a href="/search/cs?searchtype=author&query=Kira%2C+Z">Zsolt Kira</a>, <a href="/search/cs?searchtype=author&query=Szot%2C+A">Andrew Szot</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="2410.02751v1-abstract-short" style="display: inline;"> Intelligent embodied agents need to quickly adapt to new scenarios by integrating long histories of experience into decision-making. For instance, a robot in an unfamiliar house initially wouldn't know the locations of objects needed for tasks and might perform inefficiently. However, as it gathers more experience, it should learn the layout of its environment and remember where objects are, allow… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02751v1-abstract-full').style.display = 'inline'; document.getElementById('2410.02751v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.02751v1-abstract-full" style="display: none;"> Intelligent embodied agents need to quickly adapt to new scenarios by integrating long histories of experience into decision-making. For instance, a robot in an unfamiliar house initially wouldn't know the locations of objects needed for tasks and might perform inefficiently. However, as it gathers more experience, it should learn the layout of its environment and remember where objects are, allowing it to complete new tasks more efficiently. To enable such rapid adaptation to new tasks, we present ReLIC, a new approach for in-context reinforcement learning (RL) for embodied agents. With ReLIC, agents are capable of adapting to new environments using 64,000 steps of in-context experience with full attention while being trained through self-generated experience via RL. We achieve this by proposing a novel policy update scheme for on-policy RL called "partial updates'' as well as a Sink-KV mechanism that enables effective utilization of a long observation history for embodied agents. Our method outperforms a variety of meta-RL baselines in adapting to unseen houses in an embodied multi-object navigation task. In addition, we find that ReLIC is capable of few-shot imitation learning despite never being trained with expert demonstrations. We also provide a comprehensive analysis of ReLIC, highlighting that the combination of large-scale RL training, the proposed partial updates scheme, and the Sink-KV are essential for effective in-context learning. The code for ReLIC and all our experiments is at https://github.com/aielawady/relic <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.02751v1-abstract-full').style.display = 'none'; document.getElementById('2410.02751v1-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> 3 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.06939">arXiv:2407.06939</a> <span> [<a href="https://arxiv.org/pdf/2407.06939">pdf</a>, <a href="https://arxiv.org/format/2407.06939">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="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Towards Open-World Mobile Manipulation in Homes: Lessons from the Neurips 2023 HomeRobot Open Vocabulary Mobile Manipulation Challenge </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yenamandra%2C+S">Sriram Yenamandra</a>, <a href="/search/cs?searchtype=author&query=Ramachandran%2C+A">Arun Ramachandran</a>, <a href="/search/cs?searchtype=author&query=Khanna%2C+M">Mukul Khanna</a>, <a href="/search/cs?searchtype=author&query=Yadav%2C+K">Karmesh Yadav</a>, <a href="/search/cs?searchtype=author&query=Vakil%2C+J">Jay Vakil</a>, <a href="/search/cs?searchtype=author&query=Melnik%2C+A">Andrew Melnik</a>, <a href="/search/cs?searchtype=author&query=B%C3%BCttner%2C+M">Michael B眉ttner</a>, <a href="/search/cs?searchtype=author&query=Harz%2C+L">Leon Harz</a>, <a href="/search/cs?searchtype=author&query=Brown%2C+L">Lyon Brown</a>, <a href="/search/cs?searchtype=author&query=Nandi%2C+G+C">Gora Chand Nandi</a>, <a href="/search/cs?searchtype=author&query=PS%2C+A">Arjun PS</a>, <a href="/search/cs?searchtype=author&query=Yadav%2C+G+K">Gaurav Kumar Yadav</a>, <a href="/search/cs?searchtype=author&query=Kala%2C+R">Rahul Kala</a>, <a href="/search/cs?searchtype=author&query=Haschke%2C+R">Robert Haschke</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+Y">Yang Luo</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+J">Jinxin Zhu</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Y">Yansen Han</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+B">Bingyi Lu</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+X">Xuan Gu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qinyuan Liu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yaping Zhao</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+Q">Qiting Ye</a>, <a href="/search/cs?searchtype=author&query=Dou%2C+C">Chenxiao Dou</a>, <a href="/search/cs?searchtype=author&query=Chua%2C+Y">Yansong Chua</a>, <a href="/search/cs?searchtype=author&query=Kuzma%2C+V">Volodymyr Kuzma</a> , et al. (20 additional authors not shown) </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="2407.06939v1-abstract-short" style="display: inline;"> In order to develop robots that can effectively serve as versatile and capable home assistants, it is crucial for them to reliably perceive and interact with a wide variety of objects across diverse environments. To this end, we proposed Open Vocabulary Mobile Manipulation as a key benchmark task for robotics: finding any object in a novel environment and placing it on any receptacle surface withi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.06939v1-abstract-full').style.display = 'inline'; document.getElementById('2407.06939v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.06939v1-abstract-full" style="display: none;"> In order to develop robots that can effectively serve as versatile and capable home assistants, it is crucial for them to reliably perceive and interact with a wide variety of objects across diverse environments. To this end, we proposed Open Vocabulary Mobile Manipulation as a key benchmark task for robotics: finding any object in a novel environment and placing it on any receptacle surface within that environment. We organized a NeurIPS 2023 competition featuring both simulation and real-world components to evaluate solutions to this task. Our baselines on the most challenging version of this task, using real perception in simulation, achieved only an 0.8% success rate; by the end of the competition, the best participants achieved an 10.8\% success rate, a 13x improvement. We observed that the most successful teams employed a variety of methods, yet two common threads emerged among the best solutions: enhancing error detection and recovery, and improving the integration of perception with decision-making processes. In this paper, we detail the results and methodologies used, both in simulation and real-world settings. We discuss the lessons learned and their implications for future research. Additionally, we compare performance in real and simulated environments, emphasizing the necessity for robust generalization to novel settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.06939v1-abstract-full').style.display = 'none'; document.getElementById('2407.06939v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.17168">arXiv:2406.17168</a> <span> [<a href="https://arxiv.org/pdf/2406.17168">pdf</a>, <a href="https://arxiv.org/format/2406.17168">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="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Reinforcement Learning via Auxiliary Task Distillation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Harish%2C+A+N">Abhinav Narayan Harish</a>, <a href="/search/cs?searchtype=author&query=Heck%2C+L">Larry Heck</a>, <a href="/search/cs?searchtype=author&query=Hanna%2C+J+P">Josiah P. Hanna</a>, <a href="/search/cs?searchtype=author&query=Kira%2C+Z">Zsolt Kira</a>, <a href="/search/cs?searchtype=author&query=Szot%2C+A">Andrew Szot</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="2406.17168v1-abstract-short" style="display: inline;"> We present Reinforcement Learning via Auxiliary Task Distillation (AuxDistill), a new method that enables reinforcement learning (RL) to perform long-horizon robot control problems by distilling behaviors from auxiliary RL tasks. AuxDistill achieves this by concurrently carrying out multi-task RL with auxiliary tasks, which are easier to learn and relevant to the main task. A weighted distillation… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.17168v1-abstract-full').style.display = 'inline'; document.getElementById('2406.17168v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.17168v1-abstract-full" style="display: none;"> We present Reinforcement Learning via Auxiliary Task Distillation (AuxDistill), a new method that enables reinforcement learning (RL) to perform long-horizon robot control problems by distilling behaviors from auxiliary RL tasks. AuxDistill achieves this by concurrently carrying out multi-task RL with auxiliary tasks, which are easier to learn and relevant to the main task. A weighted distillation loss transfers behaviors from these auxiliary tasks to solve the main task. We demonstrate that AuxDistill can learn a pixels-to-actions policy for a challenging multi-stage embodied object rearrangement task from the environment reward without demonstrations, a learning curriculum, or pre-trained skills. AuxDistill achieves $2.3 \times$ higher success than the previous state-of-the-art baseline in the Habitat Object Rearrangement benchmark and outperforms methods that use pre-trained skills and expert demonstrations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.17168v1-abstract-full').style.display = 'none'; document.getElementById('2406.17168v1-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> 24 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.07904">arXiv:2406.07904</a> <span> [<a href="https://arxiv.org/pdf/2406.07904">pdf</a>, <a href="https://arxiv.org/format/2406.07904">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"> Grounding Multimodal Large Language Models in Actions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Szot%2C+A">Andrew Szot</a>, <a href="/search/cs?searchtype=author&query=Mazoure%2C+B">Bogdan Mazoure</a>, <a href="/search/cs?searchtype=author&query=Agrawal%2C+H">Harsh Agrawal</a>, <a href="/search/cs?searchtype=author&query=Hjelm%2C+D">Devon Hjelm</a>, <a href="/search/cs?searchtype=author&query=Kira%2C+Z">Zsolt Kira</a>, <a href="/search/cs?searchtype=author&query=Toshev%2C+A">Alexander Toshev</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="2406.07904v1-abstract-short" style="display: inline;"> Multimodal Large Language Models (MLLMs) have demonstrated a wide range of capabilities across many domains, including Embodied AI. In this work, we study how to best ground a MLLM into different embodiments and their associated action spaces, with the goal of leveraging the multimodal world knowledge of the MLLM. We first generalize a number of methods through a unified architecture and the lens… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.07904v1-abstract-full').style.display = 'inline'; document.getElementById('2406.07904v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.07904v1-abstract-full" style="display: none;"> Multimodal Large Language Models (MLLMs) have demonstrated a wide range of capabilities across many domains, including Embodied AI. In this work, we study how to best ground a MLLM into different embodiments and their associated action spaces, with the goal of leveraging the multimodal world knowledge of the MLLM. We first generalize a number of methods through a unified architecture and the lens of action space adaptors. For continuous actions, we show that a learned tokenization allows for sufficient modeling precision, yielding the best performance on downstream tasks. For discrete actions, we demonstrate that semantically aligning these actions with the native output token space of the MLLM leads to the strongest performance. We arrive at these lessons via a thorough study of seven action space adapters on five different environments, encompassing over 114 embodied tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.07904v1-abstract-full').style.display = 'none'; document.getElementById('2406.07904v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.17722">arXiv:2310.17722</a> <span> [<a href="https://arxiv.org/pdf/2310.17722">pdf</a>, <a href="https://arxiv.org/format/2310.17722">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"> Large Language Models as Generalizable Policies for Embodied Tasks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Szot%2C+A">Andrew Szot</a>, <a href="/search/cs?searchtype=author&query=Schwarzer%2C+M">Max Schwarzer</a>, <a href="/search/cs?searchtype=author&query=Agrawal%2C+H">Harsh Agrawal</a>, <a href="/search/cs?searchtype=author&query=Mazoure%2C+B">Bogdan Mazoure</a>, <a href="/search/cs?searchtype=author&query=Talbott%2C+W">Walter Talbott</a>, <a href="/search/cs?searchtype=author&query=Metcalf%2C+K">Katherine Metcalf</a>, <a href="/search/cs?searchtype=author&query=Mackraz%2C+N">Natalie Mackraz</a>, <a href="/search/cs?searchtype=author&query=Hjelm%2C+D">Devon Hjelm</a>, <a href="/search/cs?searchtype=author&query=Toshev%2C+A">Alexander Toshev</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="2310.17722v2-abstract-short" style="display: inline;"> We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained frozen LLM to take as input text instructions and visual egocentric observations and output actions directly in the environment. Using reinforcement learning, we train LLaRP to see and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.17722v2-abstract-full').style.display = 'inline'; document.getElementById('2310.17722v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.17722v2-abstract-full" style="display: none;"> We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained frozen LLM to take as input text instructions and visual egocentric observations and output actions directly in the environment. Using reinforcement learning, we train LLaRP to see and act solely through environmental interactions. We show that LLaRP is robust to complex paraphrasings of task instructions and can generalize to new tasks that require novel optimal behavior. In particular, on 1,000 unseen tasks it achieves 42% success rate, 1.7x the success rate of other common learned baselines or zero-shot applications of LLMs. Finally, to aid the community in studying language conditioned, massively multi-task, embodied AI problems we release a novel benchmark, Language Rearrangement, consisting of 150,000 training and 1,000 testing tasks for language-conditioned rearrangement. Video examples of LLaRP in unseen Language Rearrangement instructions are at https://llm-rl.github.io. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.17722v2-abstract-full').style.display = 'none'; document.getElementById('2310.17722v2-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.13724">arXiv:2310.13724</a> <span> [<a href="https://arxiv.org/pdf/2310.13724">pdf</a>, <a href="https://arxiv.org/format/2310.13724">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="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</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="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Puig%2C+X">Xavier Puig</a>, <a href="/search/cs?searchtype=author&query=Undersander%2C+E">Eric Undersander</a>, <a href="/search/cs?searchtype=author&query=Szot%2C+A">Andrew Szot</a>, <a href="/search/cs?searchtype=author&query=Cote%2C+M+D">Mikael Dallaire Cote</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+T">Tsung-Yen Yang</a>, <a href="/search/cs?searchtype=author&query=Partsey%2C+R">Ruslan Partsey</a>, <a href="/search/cs?searchtype=author&query=Desai%2C+R">Ruta Desai</a>, <a href="/search/cs?searchtype=author&query=Clegg%2C+A+W">Alexander William Clegg</a>, <a href="/search/cs?searchtype=author&query=Hlavac%2C+M">Michal Hlavac</a>, <a href="/search/cs?searchtype=author&query=Min%2C+S+Y">So Yeon Min</a>, <a href="/search/cs?searchtype=author&query=Vondru%C5%A1%2C+V">Vladim铆r Vondru拧</a>, <a href="/search/cs?searchtype=author&query=Gervet%2C+T">Theophile Gervet</a>, <a href="/search/cs?searchtype=author&query=Berges%2C+V">Vincent-Pierre Berges</a>, <a href="/search/cs?searchtype=author&query=Turner%2C+J+M">John M. Turner</a>, <a href="/search/cs?searchtype=author&query=Maksymets%2C+O">Oleksandr Maksymets</a>, <a href="/search/cs?searchtype=author&query=Kira%2C+Z">Zsolt Kira</a>, <a href="/search/cs?searchtype=author&query=Kalakrishnan%2C+M">Mrinal Kalakrishnan</a>, <a href="/search/cs?searchtype=author&query=Malik%2C+J">Jitendra Malik</a>, <a href="/search/cs?searchtype=author&query=Chaplot%2C+D+S">Devendra Singh Chaplot</a>, <a href="/search/cs?searchtype=author&query=Jain%2C+U">Unnat Jain</a>, <a href="/search/cs?searchtype=author&query=Batra%2C+D">Dhruv Batra</a>, <a href="/search/cs?searchtype=author&query=Rai%2C+A">Akshara Rai</a>, <a href="/search/cs?searchtype=author&query=Mottaghi%2C+R">Roozbeh Mottaghi</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="2310.13724v1-abstract-short" style="display: inline;"> We present Habitat 3.0: a simulation platform for studying collaborative human-robot tasks in home environments. Habitat 3.0 offers contributions across three dimensions: (1) Accurate humanoid simulation: addressing challenges in modeling complex deformable bodies and diversity in appearance and motion, all while ensuring high simulation speed. (2) Human-in-the-loop infrastructure: enabling real h… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.13724v1-abstract-full').style.display = 'inline'; document.getElementById('2310.13724v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.13724v1-abstract-full" style="display: none;"> We present Habitat 3.0: a simulation platform for studying collaborative human-robot tasks in home environments. Habitat 3.0 offers contributions across three dimensions: (1) Accurate humanoid simulation: addressing challenges in modeling complex deformable bodies and diversity in appearance and motion, all while ensuring high simulation speed. (2) Human-in-the-loop infrastructure: enabling real human interaction with simulated robots via mouse/keyboard or a VR interface, facilitating evaluation of robot policies with human input. (3) Collaborative tasks: studying two collaborative tasks, Social Navigation and Social Rearrangement. Social Navigation investigates a robot's ability to locate and follow humanoid avatars in unseen environments, whereas Social Rearrangement addresses collaboration between a humanoid and robot while rearranging a scene. These contributions allow us to study end-to-end learned and heuristic baselines for human-robot collaboration in-depth, as well as evaluate them with humans in the loop. Our experiments demonstrate that learned robot policies lead to efficient task completion when collaborating with unseen humanoid agents and human partners that might exhibit behaviors that the robot has not seen before. Additionally, we observe emergent behaviors during collaborative task execution, such as the robot yielding space when obstructing a humanoid agent, thereby allowing the effective completion of the task by the humanoid agent. Furthermore, our experiments using the human-in-the-loop tool demonstrate that our automated evaluation with humanoids can provide an indication of the relative ordering of different policies when evaluated with real human collaborators. Habitat 3.0 unlocks interesting new features in simulators for Embodied AI, and we hope it paves the way for a new frontier of embodied human-AI interaction capabilities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.13724v1-abstract-full').style.display = 'none'; document.getElementById('2310.13724v1-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 October, 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">Project page: http://aihabitat.org/habitat3</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.09873">arXiv:2308.09873</a> <span> [<a href="https://arxiv.org/pdf/2308.09873">pdf</a>, <a href="https://arxiv.org/format/2308.09873">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"> Skill Transformer: A Monolithic Policy for Mobile Manipulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+X">Xiaoyu Huang</a>, <a href="/search/cs?searchtype=author&query=Batra%2C+D">Dhruv Batra</a>, <a href="/search/cs?searchtype=author&query=Rai%2C+A">Akshara Rai</a>, <a href="/search/cs?searchtype=author&query=Szot%2C+A">Andrew Szot</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="2308.09873v1-abstract-short" style="display: inline;"> We present Skill Transformer, an approach for solving long-horizon robotic tasks by combining conditional sequence modeling and skill modularity. Conditioned on egocentric and proprioceptive observations of a robot, Skill Transformer is trained end-to-end to predict both a high-level skill (e.g., navigation, picking, placing), and a whole-body low-level action (e.g., base and arm motion), using a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.09873v1-abstract-full').style.display = 'inline'; document.getElementById('2308.09873v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.09873v1-abstract-full" style="display: none;"> We present Skill Transformer, an approach for solving long-horizon robotic tasks by combining conditional sequence modeling and skill modularity. Conditioned on egocentric and proprioceptive observations of a robot, Skill Transformer is trained end-to-end to predict both a high-level skill (e.g., navigation, picking, placing), and a whole-body low-level action (e.g., base and arm motion), using a transformer architecture and demonstration trajectories that solve the full task. It retains the composability and modularity of the overall task through a skill predictor module while reasoning about low-level actions and avoiding hand-off errors, common in modular approaches. We test Skill Transformer on an embodied rearrangement benchmark and find it performs robust task planning and low-level control in new scenarios, achieving a 2.5x higher success rate than baselines in hard rearrangement problems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.09873v1-abstract-full').style.display = 'none'; document.getElementById('2308.09873v1-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> 18 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.07552">arXiv:2306.07552</a> <span> [<a href="https://arxiv.org/pdf/2306.07552">pdf</a>, <a href="https://arxiv.org/format/2306.07552">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="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Berges%2C+V">Vincent-Pierre Berges</a>, <a href="/search/cs?searchtype=author&query=Szot%2C+A">Andrew Szot</a>, <a href="/search/cs?searchtype=author&query=Chaplot%2C+D+S">Devendra Singh Chaplot</a>, <a href="/search/cs?searchtype=author&query=Gokaslan%2C+A">Aaron Gokaslan</a>, <a href="/search/cs?searchtype=author&query=Mottaghi%2C+R">Roozbeh Mottaghi</a>, <a href="/search/cs?searchtype=author&query=Batra%2C+D">Dhruv Batra</a>, <a href="/search/cs?searchtype=author&query=Undersander%2C+E">Eric Undersander</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="2306.07552v1-abstract-short" style="display: inline;"> We present Galactic, a large-scale simulation and reinforcement-learning (RL) framework for robotic mobile manipulation in indoor environments. Specifically, a Fetch robot (equipped with a mobile base, 7DoF arm, RGBD camera, egomotion, and onboard sensing) is spawned in a home environment and asked to rearrange objects - by navigating to an object, picking it up, navigating to a target location, a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.07552v1-abstract-full').style.display = 'inline'; document.getElementById('2306.07552v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.07552v1-abstract-full" style="display: none;"> We present Galactic, a large-scale simulation and reinforcement-learning (RL) framework for robotic mobile manipulation in indoor environments. Specifically, a Fetch robot (equipped with a mobile base, 7DoF arm, RGBD camera, egomotion, and onboard sensing) is spawned in a home environment and asked to rearrange objects - by navigating to an object, picking it up, navigating to a target location, and then placing the object at the target location. Galactic is fast. In terms of simulation speed (rendering + physics), Galactic achieves over 421,000 steps-per-second (SPS) on an 8-GPU node, which is 54x faster than Habitat 2.0 (7699 SPS). More importantly, Galactic was designed to optimize the entire rendering + physics + RL interplay since any bottleneck in the interplay slows down training. In terms of simulation+RL speed (rendering + physics + inference + learning), Galactic achieves over 108,000 SPS, which 88x faster than Habitat 2.0 (1243 SPS). These massive speed-ups not only drastically cut the wall-clock training time of existing experiments, but also unlock an unprecedented scale of new experiments. First, Galactic can train a mobile pick skill to >80% accuracy in under 16 minutes, a 100x speedup compared to the over 24 hours it takes to train the same skill in Habitat 2.0. Second, we use Galactic to perform the largest-scale experiment to date for rearrangement using 5B steps of experience in 46 hours, which is equivalent to 20 years of robot experience. This scaling results in a single neural network composed of task-agnostic components achieving 85% success in GeometricGoal rearrangement, compared to 0% success reported in Habitat 2.0 for the same approach. The code is available at github.com/facebookresearch/galactic. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.07552v1-abstract-full').style.display = 'none'; document.getElementById('2306.07552v1-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 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/2306.00087">arXiv:2306.00087</a> <span> [<a href="https://arxiv.org/pdf/2306.00087">pdf</a>, <a href="https://arxiv.org/format/2306.00087">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="Multiagent Systems">cs.MA</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"> Adaptive Coordination in Social Embodied Rearrangement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Szot%2C+A">Andrew Szot</a>, <a href="/search/cs?searchtype=author&query=Jain%2C+U">Unnat Jain</a>, <a href="/search/cs?searchtype=author&query=Batra%2C+D">Dhruv Batra</a>, <a href="/search/cs?searchtype=author&query=Kira%2C+Z">Zsolt Kira</a>, <a href="/search/cs?searchtype=author&query=Desai%2C+R">Ruta Desai</a>, <a href="/search/cs?searchtype=author&query=Rai%2C+A">Akshara Rai</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="2306.00087v1-abstract-short" style="display: inline;"> We present the task of "Social Rearrangement", consisting of cooperative everyday tasks like setting up the dinner table, tidying a house or unpacking groceries in a simulated multi-agent environment. In Social Rearrangement, two robots coordinate to complete a long-horizon task, using onboard sensing and egocentric observations, and no privileged information about the environment. We study zero-s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.00087v1-abstract-full').style.display = 'inline'; document.getElementById('2306.00087v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.00087v1-abstract-full" style="display: none;"> We present the task of "Social Rearrangement", consisting of cooperative everyday tasks like setting up the dinner table, tidying a house or unpacking groceries in a simulated multi-agent environment. In Social Rearrangement, two robots coordinate to complete a long-horizon task, using onboard sensing and egocentric observations, and no privileged information about the environment. We study zero-shot coordination (ZSC) in this task, where an agent collaborates with a new partner, emulating a scenario where a robot collaborates with a new human partner. Prior ZSC approaches struggle to generalize in our complex and visually rich setting, and on further analysis, we find that they fail to generate diverse coordination behaviors at training time. To counter this, we propose Behavior Diversity Play (BDP), a novel ZSC approach that encourages diversity through a discriminability objective. Our results demonstrate that BDP learns adaptive agents that can tackle visual coordination, and zero-shot generalize to new partners in unseen environments, achieving 35% higher success and 32% higher efficiency compared to baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.00087v1-abstract-full').style.display = 'none'; document.getElementById('2306.00087v1-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> 31 May, 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/2303.16194">arXiv:2303.16194</a> <span> [<a href="https://arxiv.org/pdf/2303.16194">pdf</a>, <a href="https://arxiv.org/format/2303.16194">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"> BC-IRL: Learning Generalizable Reward Functions from Demonstrations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Szot%2C+A">Andrew Szot</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+A">Amy Zhang</a>, <a href="/search/cs?searchtype=author&query=Batra%2C+D">Dhruv Batra</a>, <a href="/search/cs?searchtype=author&query=Kira%2C+Z">Zsolt Kira</a>, <a href="/search/cs?searchtype=author&query=Meier%2C+F">Franziska Meier</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="2303.16194v1-abstract-short" style="display: inline;"> How well do reward functions learned with inverse reinforcement learning (IRL) generalize? We illustrate that state-of-the-art IRL algorithms, which maximize a maximum-entropy objective, learn rewards that overfit to the demonstrations. Such rewards struggle to provide meaningful rewards for states not covered by the demonstrations, a major detriment when using the reward to learn policies in new… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.16194v1-abstract-full').style.display = 'inline'; document.getElementById('2303.16194v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.16194v1-abstract-full" style="display: none;"> How well do reward functions learned with inverse reinforcement learning (IRL) generalize? We illustrate that state-of-the-art IRL algorithms, which maximize a maximum-entropy objective, learn rewards that overfit to the demonstrations. Such rewards struggle to provide meaningful rewards for states not covered by the demonstrations, a major detriment when using the reward to learn policies in new situations. We introduce BC-IRL a new inverse reinforcement learning method that learns reward functions that generalize better when compared to maximum-entropy IRL approaches. In contrast to the MaxEnt framework, which learns to maximize rewards around demonstrations, BC-IRL updates reward parameters such that the policy trained with the new reward matches the expert demonstrations better. We show that BC-IRL learns rewards that generalize better on an illustrative simple task and two continuous robotic control tasks, achieving over twice the success rate of baselines in challenging generalization settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.16194v1-abstract-full').style.display = 'none'; document.getElementById('2303.16194v1-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> 28 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.06849">arXiv:2210.06849</a> <span> [<a href="https://arxiv.org/pdf/2210.06849">pdf</a>, <a href="https://arxiv.org/format/2210.06849">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Retrospectives on the Embodied AI Workshop </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Deitke%2C+M">Matt Deitke</a>, <a href="/search/cs?searchtype=author&query=Batra%2C+D">Dhruv Batra</a>, <a href="/search/cs?searchtype=author&query=Bisk%2C+Y">Yonatan Bisk</a>, <a href="/search/cs?searchtype=author&query=Campari%2C+T">Tommaso Campari</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+A+X">Angel X. Chang</a>, <a href="/search/cs?searchtype=author&query=Chaplot%2C+D+S">Devendra Singh Chaplot</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Changan Chen</a>, <a href="/search/cs?searchtype=author&query=D%27Arpino%2C+C+P">Claudia P茅rez D'Arpino</a>, <a href="/search/cs?searchtype=author&query=Ehsani%2C+K">Kiana Ehsani</a>, <a href="/search/cs?searchtype=author&query=Farhadi%2C+A">Ali Farhadi</a>, <a href="/search/cs?searchtype=author&query=Fei-Fei%2C+L">Li Fei-Fei</a>, <a href="/search/cs?searchtype=author&query=Francis%2C+A">Anthony Francis</a>, <a href="/search/cs?searchtype=author&query=Gan%2C+C">Chuang Gan</a>, <a href="/search/cs?searchtype=author&query=Grauman%2C+K">Kristen Grauman</a>, <a href="/search/cs?searchtype=author&query=Hall%2C+D">David Hall</a>, <a href="/search/cs?searchtype=author&query=Han%2C+W">Winson Han</a>, <a href="/search/cs?searchtype=author&query=Jain%2C+U">Unnat Jain</a>, <a href="/search/cs?searchtype=author&query=Kembhavi%2C+A">Aniruddha Kembhavi</a>, <a href="/search/cs?searchtype=author&query=Krantz%2C+J">Jacob Krantz</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+S">Stefan Lee</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chengshu Li</a>, <a href="/search/cs?searchtype=author&query=Majumder%2C+S">Sagnik Majumder</a>, <a href="/search/cs?searchtype=author&query=Maksymets%2C+O">Oleksandr Maksymets</a>, <a href="/search/cs?searchtype=author&query=Mart%C3%ADn-Mart%C3%ADn%2C+R">Roberto Mart铆n-Mart铆n</a>, <a href="/search/cs?searchtype=author&query=Mottaghi%2C+R">Roozbeh Mottaghi</a> , et al. (14 additional authors not shown) </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="2210.06849v3-abstract-short" style="display: inline;"> We present a retrospective on the state of Embodied AI research. Our analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are grouped into three themes: (1) visual navigation, (2) rearrangement, and (3) embodied vision-and-language. We discuss the dominant datasets within each theme, evaluation metrics for the challenges, and the performance of state-of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.06849v3-abstract-full').style.display = 'inline'; document.getElementById('2210.06849v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.06849v3-abstract-full" style="display: none;"> We present a retrospective on the state of Embodied AI research. Our analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are grouped into three themes: (1) visual navigation, (2) rearrangement, and (3) embodied vision-and-language. We discuss the dominant datasets within each theme, evaluation metrics for the challenges, and the performance of state-of-the-art models. We highlight commonalities between top approaches to the challenges and identify potential future directions for Embodied AI research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.06849v3-abstract-full').style.display = 'none'; document.getElementById('2210.06849v3-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> 4 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.10712">arXiv:2205.10712</a> <span> [<a href="https://arxiv.org/pdf/2205.10712">pdf</a>, <a href="https://arxiv.org/format/2205.10712">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Housekeep: Tidying Virtual Households using Commonsense Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kant%2C+Y">Yash Kant</a>, <a href="/search/cs?searchtype=author&query=Ramachandran%2C+A">Arun Ramachandran</a>, <a href="/search/cs?searchtype=author&query=Yenamandra%2C+S">Sriram Yenamandra</a>, <a href="/search/cs?searchtype=author&query=Gilitschenski%2C+I">Igor Gilitschenski</a>, <a href="/search/cs?searchtype=author&query=Batra%2C+D">Dhruv Batra</a>, <a href="/search/cs?searchtype=author&query=Szot%2C+A">Andrew Szot</a>, <a href="/search/cs?searchtype=author&query=Agrawal%2C+H">Harsh Agrawal</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="2205.10712v1-abstract-short" style="display: inline;"> We introduce Housekeep, a benchmark to evaluate commonsense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by rearranging misplaced objects without explicit instructions specifying which objects need to be rearranged. Instead, the agent must learn from and is evaluated against human preferences of which objects belong where in a tidy house. Specifically, w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.10712v1-abstract-full').style.display = 'inline'; document.getElementById('2205.10712v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.10712v1-abstract-full" style="display: none;"> We introduce Housekeep, a benchmark to evaluate commonsense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by rearranging misplaced objects without explicit instructions specifying which objects need to be rearranged. Instead, the agent must learn from and is evaluated against human preferences of which objects belong where in a tidy house. Specifically, we collect a dataset of where humans typically place objects in tidy and untidy houses constituting 1799 objects, 268 object categories, 585 placements, and 105 rooms. Next, we propose a modular baseline approach for Housekeep that integrates planning, exploration, and navigation. It leverages a fine-tuned large language model (LLM) trained on an internet text corpus for effective planning. We show that our baseline agent generalizes to rearranging unseen objects in unknown environments. See our webpage for more details: https://yashkant.github.io/housekeep/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.10712v1-abstract-full').style.display = 'none'; document.getElementById('2205.10712v1-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 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.14405">arXiv:2106.14405</a> <span> [<a href="https://arxiv.org/pdf/2106.14405">pdf</a>, <a href="https://arxiv.org/format/2106.14405">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="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Habitat 2.0: Training Home Assistants to Rearrange their Habitat </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Szot%2C+A">Andrew Szot</a>, <a href="/search/cs?searchtype=author&query=Clegg%2C+A">Alex Clegg</a>, <a href="/search/cs?searchtype=author&query=Undersander%2C+E">Eric Undersander</a>, <a href="/search/cs?searchtype=author&query=Wijmans%2C+E">Erik Wijmans</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yili Zhao</a>, <a href="/search/cs?searchtype=author&query=Turner%2C+J">John Turner</a>, <a href="/search/cs?searchtype=author&query=Maestre%2C+N">Noah Maestre</a>, <a href="/search/cs?searchtype=author&query=Mukadam%2C+M">Mustafa Mukadam</a>, <a href="/search/cs?searchtype=author&query=Chaplot%2C+D">Devendra Chaplot</a>, <a href="/search/cs?searchtype=author&query=Maksymets%2C+O">Oleksandr Maksymets</a>, <a href="/search/cs?searchtype=author&query=Gokaslan%2C+A">Aaron Gokaslan</a>, <a href="/search/cs?searchtype=author&query=Vondrus%2C+V">Vladimir Vondrus</a>, <a href="/search/cs?searchtype=author&query=Dharur%2C+S">Sameer Dharur</a>, <a href="/search/cs?searchtype=author&query=Meier%2C+F">Franziska Meier</a>, <a href="/search/cs?searchtype=author&query=Galuba%2C+W">Wojciech Galuba</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+A">Angel Chang</a>, <a href="/search/cs?searchtype=author&query=Kira%2C+Z">Zsolt Kira</a>, <a href="/search/cs?searchtype=author&query=Koltun%2C+V">Vladlen Koltun</a>, <a href="/search/cs?searchtype=author&query=Malik%2C+J">Jitendra Malik</a>, <a href="/search/cs?searchtype=author&query=Savva%2C+M">Manolis Savva</a>, <a href="/search/cs?searchtype=author&query=Batra%2C+D">Dhruv Batra</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="2106.14405v2-abstract-short" style="display: inline;"> We introduce Habitat 2.0 (H2.0), a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios. We make comprehensive contributions to all levels of the embodied AI stack - data, simulation, and benchmark tasks. Specifically, we present: (i) ReplicaCAD: an artist-authored, annotated, reconfigurable 3D dataset of apartments (matching real spa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.14405v2-abstract-full').style.display = 'inline'; document.getElementById('2106.14405v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.14405v2-abstract-full" style="display: none;"> We introduce Habitat 2.0 (H2.0), a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios. We make comprehensive contributions to all levels of the embodied AI stack - data, simulation, and benchmark tasks. Specifically, we present: (i) ReplicaCAD: an artist-authored, annotated, reconfigurable 3D dataset of apartments (matching real spaces) with articulated objects (e.g. cabinets and drawers that can open/close); (ii) H2.0: a high-performance physics-enabled 3D simulator with speeds exceeding 25,000 simulation steps per second (850x real-time) on an 8-GPU node, representing 100x speed-ups over prior work; and, (iii) Home Assistant Benchmark (HAB): a suite of common tasks for assistive robots (tidy the house, prepare groceries, set the table) that test a range of mobile manipulation capabilities. These large-scale engineering contributions allow us to systematically compare deep reinforcement learning (RL) at scale and classical sense-plan-act (SPA) pipelines in long-horizon structured tasks, with an emphasis on generalization to new objects, receptacles, and layouts. We find that (1) flat RL policies struggle on HAB compared to hierarchical ones; (2) a hierarchy with independent skills suffers from 'hand-off problems', and (3) SPA pipelines are more brittle than RL policies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.14405v2-abstract-full').style.display = 'none'; document.getElementById('2106.14405v2-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2011.01928">arXiv:2011.01928</a> <span> [<a href="https://arxiv.org/pdf/2011.01928">pdf</a>, <a href="https://arxiv.org/format/2011.01928">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="Robotics">cs.RO</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"> Generalization to New Actions in Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jain%2C+A">Ayush Jain</a>, <a href="/search/cs?searchtype=author&query=Szot%2C+A">Andrew Szot</a>, <a href="/search/cs?searchtype=author&query=Lim%2C+J+J">Joseph J. Lim</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="2011.01928v1-abstract-short" style="display: inline;"> A fundamental trait of intelligence is the ability to achieve goals in the face of novel circumstances, such as making decisions from new action choices. However, standard reinforcement learning assumes a fixed set of actions and requires expensive retraining when given a new action set. To make learning agents more adaptable, we introduce the problem of zero-shot generalization to new actions. We… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.01928v1-abstract-full').style.display = 'inline'; document.getElementById('2011.01928v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2011.01928v1-abstract-full" style="display: none;"> A fundamental trait of intelligence is the ability to achieve goals in the face of novel circumstances, such as making decisions from new action choices. However, standard reinforcement learning assumes a fixed set of actions and requires expensive retraining when given a new action set. To make learning agents more adaptable, we introduce the problem of zero-shot generalization to new actions. We propose a two-stage framework where the agent first infers action representations from action information acquired separately from the task. A policy flexible to varying action sets is then trained with generalization objectives. We benchmark generalization on sequential tasks, such as selecting from an unseen tool-set to solve physical reasoning puzzles and stacking towers with novel 3D shapes. Videos and code are available at https://sites.google.com/view/action-generalization <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.01928v1-abstract-full').style.display = 'none'; document.getElementById('2011.01928v1-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> 3 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">ICML 2020. Videos and code: https://sites.google.com/view/action-generalization</span> </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