<div dir="ltr"><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">AAAI Spring Symposium on Challenges and Opportunities for Multi-Agent </span><span style="font-family:Arial;font-size:11pt;white-space:pre-wrap">Reinforcement Learning (COMARL) 2021</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-family:Arial;font-size:11pt;white-space:pre-wrap">March 22-24, 2021, Stanford University in Palo Alto, California, USA.</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><br></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="text-decoration-line:underline;font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><a href="https://sites.google.com/corp/view/comarl-aaai-2021/call-for-papers" style="text-decoration-line:none">https://sites.google.com/corp/view/comarl-aaai-2021/call-for-papers</a></span><span style="font-variant-numeric:normal;font-variant-east-asian:normal;font-size:11pt;font-family:Arial;vertical-align:baseline;white-space:pre-wrap"> </span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-family:Arial;font-size:11pt;white-space:pre-wrap"><br></span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-family:Arial;font-size:11pt;white-space:pre-wrap">Key Dates:</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;padding:0pt 0pt 0pt 30pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Submission: November 1st, 2020, 23:59 GMT</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;padding:0pt 0pt 0pt 30pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Notification: December 3rd, 2020</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;padding:0pt 0pt 0pt 30pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Symposium: March 22–24, 2021</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;padding:0pt 0pt 0pt 30pt"><br></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Call for position papers to define a topic of study at the symposium:<br></span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><br></span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">We live in a multi-agent world and to be successful in that world intelligent agents will need to learn to take into account the agency of others. They will need to compete in market places, cooperate in teams, communicate with others, coordinate their plans, and negotiate outcomes. Examples include self-driving cars interacting in traffic, personal</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">assistants acting on behalf of humans and negotiating with other agents, swarms of unmanned aerial vehicles, financial trading systems, robotic teams, and household robots.</span></p><br><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">There has been a lot of great work on multi-agent reinforcement learning (MARL) in the past decade, but significant challenges remain, including:</span></p><ul style="margin-top:0px;margin-bottom:0px"><li style="list-style-type:disc;font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">the difficulty of learning an optimal model/policy from a partial signal,</span></p></li><li style="list-style-type:disc;font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">learning to cooperate/compete in non-stationary environments with</span></p></li><li style="list-style-type:disc;font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">distributed, simultaneously learning agents,</span></p></li><li style="list-style-type:disc;font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">the interplay between abstraction and influence of other agents,</span></p></li><li style="list-style-type:disc;font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">the exploration vs. exploitation dilemma,</span></p></li><li style="list-style-type:disc;font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">the scalability and effectiveness of learning algorithms,</span></p></li><li style="list-style-type:disc;font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">avoiding social dilemmas, and</span></p></li><li style="list-style-type:disc;font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">learning emergent communication.</span></p></li></ul><br><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">The purpose of this symposium is to bring together researchers in multiagent reinforcement learning, but also more widely machine learning and multiagent systems, to explore some of these and other challenges in more detail. The main goal is to broaden the scope of MARL research and to address the fundamental issues that hinder the applicability of MARL for solving complex real world problems.</span></p><br><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">We aim to organize an active workshop, with many interactive (brainstorm/breakout) sessions. We are hopeful that this will form the basis for ongoing collaborations on these challenges between the attendants and we aim for several position papers as concrete outcomes.</span></p><br><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Authors can submit papers of 1-4 pages that will be reviewed by the organizing committee. We are looking for position papers that present a challenge or opportunity for MARL research, which should be on a topic the authors not only wish to interact on but also ‘work’ on with other participants during the symposium. We also welcome (preliminary) research papers that describe new perspectives to dealing with MARL challenges, but we are not looking for summaries of current research---papers should clearly state some limitation(s) of current methods and potential ways these could be overcome. Submissions will be handled through easychair: </span><a href="https://easychair.org/conferences/?conf=sss21" style="text-decoration-line:none"><span style="font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;text-decoration-line:underline;vertical-align:baseline;white-space:pre-wrap">https://easychair.org/conferences/?conf=sss21</span></a></p><br><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">-----------------------------------------------------------------------------------------------------------------</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Special note for authors of papers accepted to last year’s COMARL 2020 symposium</span></p><br><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">As communicated earlier, we are pleased to announce that all of the papers previously accepted to COMARL 2020 (postponed due to COVID-19) will, of course, naturally be presented at COMARL 2021.</span></p><br><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Moreover, given the time lapsed since the 2020 session, we would like to offer authors who had their papers accepted for the March 2020 session the following options for the 2021 session:</span></p><ol style="margin-top:0px;margin-bottom:0px"><li style="list-style-type:decimal;font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p style="line-height:1.38;margin-top:10pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Presenting their 2020 paper as-is in the new session.</span></p></li><li style="list-style-type:decimal;font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Submitting a minor revision of their paper (i.e., minor updates/improvements, and no major change in topic). The organizing committee will subsequently verify the changes are minor (i.e., a minimal review).</span></p></li><li style="list-style-type:decimal;font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Conduct a major revision of their 2020 paper. This will involve a full review by the PC.</span></p></li><li style="list-style-type:decimal;font-size:11pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p style="line-height:1.38;margin-top:0pt;margin-bottom:10pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Submitting a new paper altogether (and choosing to also present their 2020 paper as-is). This will involve a full review by the PC.</span></p></li></ol><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">The deadline for submissions of minor, major, and new papers (Options 2-4 above) is November 1st, 2020, 23:59 GMT, with submissions made on <a href="https://easychair.org/conferences/?conf=sss21">https://easychair.org/conferences/?conf=sss21</a>. Please let us know your preferences as soon as possible. </span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">-----------------------------------------------------------------------------------------------------------------</span></p><br><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Best regards,</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;padding:0pt 0pt 0pt 30pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Organizing Committee:</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;padding:0pt 0pt 0pt 30pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Christopher Amato, Northeastern University</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;padding:0pt 0pt 0pt 30pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Frans Oliehoek, Delft University of Technology</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;padding:0pt 0pt 0pt 30pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Shayegan Omidshafiei, Google DeepMind</span></p><p style="line-height:1.38;margin-top:0pt;margin-bottom:0pt;padding:0pt 0pt 0pt 30pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Karl Tuyls, Google DeepMind</span></p></div>