<div dir="ltr"><div>Hi all,</div><div><br></div><div>A quick reminder that the deadline is approaching: this Monday, November 9th!</div><div><br></div><div>Thanks,</div><div>Marc</div><div><br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Tue, Sep 22, 2020 at 1:32 PM Marc Lanctot <<a href="mailto:marc.lanctot@gmail.com">marc.lanctot@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><b><p><span><span style="font-weight:normal">[Apologies for multiple cross-posting!]</span></span></p><p><span><span style="font-weight:normal"></span><br></span></p><p dir="ltr"><span>Call for Participation: AAAI 2021 Workshop on Reinforcement Learning in Games</span></p><p dir="ltr"><span>Submission Deadline: </span><span style="color:red">November 9, 2020</span></p></b><b><p dir="ltr"><span>Website:</span><a href="http://aaai-rlg.mlanctot.info/" rel="nofollow" target="_blank"><span> </span><span style="text-decoration:underline">http://aaai-rlg.mlanctot.info/</span></a></p><p dir="ltr"><br></p></b><p dir="ltr"><span>Games
provide an abstract and formal model of environments in which multiple
agents interact: each player has a well-defined goal and rules to
describe the effects of interactions among the players. The first
achievements in playing these games at super-human level were attained
with methods that relied on and exploited domain expertise that was
designed manually (e.g. chess, checkers). In recent years, we have seen
examples of general approaches that learn to play these games via
self-play reinforcement learning (RL), as first demonstrated in
Backgammon. While progress has been impressive, we believe we have just
scratched the surface of what is capable, and much work remains to be
done in order to truly understand the algorithms and learning processes
within these environments.</span></p><p dir="ltr"><span>The main
objective of the workshop is to bring researchers together to discuss
ideas, preliminary results, and ongoing research in the field of
reinforcement in games. <br></span></p><p dir="ltr"><span>We invite participants to submit papers on the 9th of November, based on but not limited to, the following topics: <br></span></p><ul><li><span>RL
in various formalisms: one-shot games, turn-based, and Markov games,
partially-observable games, continuous games, cooperative games</span></li><li><span>Deep RL in games</span></li><li><span>Combining search and RL in games</span></li><li><span>Inverse RL in games</span></li><li><span>Foundations, theory, and game-theoretic algorithms for RL</span></li><li><span>Opponent modeling</span></li><li><span>Analyses of learning dynamics in games</span></li><li><span>Evolutionary methods for RL in games</span></li><li><span>RL in games without the rules</span></li><li><span>Monte Carlo tree search</span></li><li><span>Online learning in games.</span></li></ul><p dir="ltr"><span>**Format of workshop** <br></span></p><p dir="ltr"><span>RLG
is a 1 full-day workshop. It will start a 60 minute mini-tutorial
covering a brief tutorial and basics of RL in games, 2-3 invited talks
by prominent contributors to the field, paper presentations, a poster
session, and will close with a discussion panel.</span></p><div><span>**Submission requirements**</span></div><div><span><br></span></div><div><span>Papers
must be between 4-8 pages in the AAAI submission format, with the
eighth page containing only references. Papers will be submitted
electronically using Easychair. Accepted papers will </span><span style="font-style:italic">not</span><span>
be archival, and we explicitly allow papers that are concurrently
submitted to, currently under review at, or recently accepted in other
conferences / venues.</span></div><p dir="ltr"><span><br></span></p><p dir="ltr"><span>Please submit your paper using</span><span> the submission link on the web site.<br></span></p><p dir="ltr"><span>Workshop Chair: Martin Schmid (</span>DeepMind<span style="text-decoration:underline">)</span><span></span></p><p dir="ltr"><span>Workshop committee: Marc Lanctot (DeepMind</span><span></span><span>), Julien Perolat (DeepMind</span><span></span><span>), Martin Schmid (DeepMind</span><span>).</span></p></div>
</blockquote></div>