AAAI Spring Symposium on Challenges and Opportunities for Multi-Agent Reinforcement Learning (COMARL) March 23-25 2020, Stanford University in Palo Alto, California, USA
https://sites.google.com/corp/view/comarl-aaai-2020/ Call for participation: Help us define and solve the big challenges in multiagent reinforcement learning. 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 marketplaces, cooperate in teams, communicate with others, coordinate their plans, and negotiate outcomes. Examples include self-driving cars interacting in traffic, personal assistants acting on behalf of humans and negotiating with other agents, swarms of unmanned aerial vehicles, financial trading systems, robotic teams, and household robots. There has been a lot of great work on multi-agent reinforcement learning (MARL) in the past decade, but significant challenges remain, including: -how can we understand and control the dynamics of interacting learners? -how to benchmark multiagent learning (and multiagent systems more generally)? -how to learn to communicate? (emergent communication) -how to use MARL in such a way that brings more than single agent RL in real applications? 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 overall 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. To make a concrete step towards this overall goal, 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 one or more position papers as concrete outcomes. To facilitate this process, we will ask participants to fill out a short survey (takes just a few minutes) about their perspective on the challenges in MARL. The organizers will use this information to kick-start the discussions: https://forms.gle/AKRSwMWFBpKebBWY8 Invited speakers include: Craig Boutilier (Google), Romuald Elie (University Paris-Est), Jakob Foerster (FAIR), Thore Graepel (DeepMind), Edward Lockhart (DeepMind), Georgios Piliouras (SUTD) Organizing Committee: Christopher Amato, Northeastern University Frans Oliehoek, Delft University of Technology Shayegan Omidshafiei, Google DeepMind Karl Tuyls, Google DeepMind Christopher Amato Assistant Professor Khoury College of Computer Sciences Northeastern University http://www.ccs.neu.edu/home/camato/
_______________________________________________ uai mailing list [email protected] https://secure.engr.oregonstate.edu/mailman/listinfo/uai
