Timezone: »
This paper investigates generalisation in multi-agent games, where the generality of the agent can be evaluated by playing against opponents it hasn't seen during training. We propose two new games with concealed information and complex, non-transitive reward structure (think rock-paper-scissors). It turns out that most current deep reinforcement learning methods fail to efficiently explore the strategy space, thus learning policies that generalise poorly to unseen opponents. We then propose a novel hierarchical agent architecture, where the hierarchy is grounded in the game-theoretic structure of the game -- the top level chooses strategic responses to opponents, while the low level implements them into policy over primitive actions. This grounding facilitates credit assignment across the levels of hierarchy. Our experiments show that the proposed hierarchical agent is capable of generalisation to unseen opponents, while conventional baselines fail to generalise whatsoever.
Author Information
Alexander Vezhnevets (DeepMind)
Yuhuai Wu (University of Toronto)
Maria Eckstein (UC Berkeley)
Rémi Leblond (DeepMind)
Joel Z Leibo (DeepMind)
More from the Same Authors
-
2021 Poster: Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot »
Joel Z Leibo · Edgar Duenez-Guzman · Alexander Vezhnevets · John Agapiou · Peter Sunehag · Raphael Koster · Jayd Matyas · Charles Beattie · Igor Mordatch · Thore Graepel -
2021 Oral: Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot »
Joel Z Leibo · Edgar Duenez-Guzman · Alexander Vezhnevets · John Agapiou · Peter Sunehag · Raphael Koster · Jayd Matyas · Charles Beattie · Igor Mordatch · Thore Graepel -
2019 Poster: Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning »
Natasha Jaques · Angeliki Lazaridou · Edward Hughes · Caglar Gulcehre · Pedro Ortega · DJ Strouse · Joel Z Leibo · Nando de Freitas -
2019 Oral: Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning »
Natasha Jaques · Angeliki Lazaridou · Edward Hughes · Caglar Gulcehre · Pedro Ortega · DJ Strouse · Joel Z Leibo · Nando de Freitas -
2017 Poster: FeUdal Networks for Hierarchical Reinforcement Learning »
Alexander Vezhnevets · Simon Osindero · Tom Schaul · Nicolas Heess · Max Jaderberg · David Silver · Koray Kavukcuoglu -
2017 Talk: FeUdal Networks for Hierarchical Reinforcement Learning »
Alexander Vezhnevets · Simon Osindero · Tom Schaul · Nicolas Heess · Max Jaderberg · David Silver · Koray Kavukcuoglu