Developing, evaluating and scaling learning agents in multi-agent environments
Ian Gemp, Thomas Anthony, Yoram Bachrach, Avishkar Bhoopchand, Kalesha Bullard, Jerome T. Connor, Vibhavari Dasagi, Bart De Vylder, Edgar A. Duéñez‐Guzmán, Romuald Élie, Richard Everett, Daniel Hennes, Edward Hughes, Mina Khan, Marc Lanctot, Kate S. Larson, Guy Lever, Siqi Liu, Luke Marris, Kevin Robert McKee · AI Communications · 2022
The Game Theory & Multi-Agent team at DeepMind studies several aspects of multi-agent learning ranging from computing approximations to fundamental concepts in game theory to simulating social dilemmas in rich spatial environments and training 3-d humanoids in difficult team coordination tasks. A signature aim of our group is to use the resources and expertise made available to us at DeepMind in deep reinforcement learning to explore multi-agent systems in complex environments and use these benchmarks to advance our understanding. Here, we summarise the recent work of our team and present a taxonomy that we feel highlights many important open challenges in multi-agent research.