Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning

Hengyuan Hu, Jakob N Foerster

Keywords: adversarial, multi agent reinforcement learning, reinforcement learning

Mon Session 4 (17:00-19:00 GMT) [Live QA] [Cal]
Mon Session 5 (20:00-22:00 GMT) [Live QA] [Cal]
Monday: Multiagent Systems

Abstract: In recent years we have seen fast progress on a number of benchmark problems in AI, with modern methods achieving near or super human performance in Go, Poker and Dota. One common aspect of all of these challenges is that they are by design adversarial or, technically speaking, zero-sum. In contrast to these settings, success in the real world commonly requires humans to collaborate and communicate with others, in settings that are, at least partially, cooperative. In the last year, the card game Hanabi has been established as a new benchmark environment for AI to fill this gap. In particular, Hanabi is interesting to humans since it is entirely focused on theory of mind, i.e. the ability to effectively reason over the intentions, beliefs and point of view of other agents when observing their actions. Learning to be informative when observed by others is an interesting challenge for Reinforcement Learning (RL): Fundamentally, RL requires agents to explore in order to discover good policies. However, when done naively, this randomness will inherently make their actions less informative to others during training. We present a new deep multi-agent RL method, the Simplified Action Decoder (SAD), which resolves this contradiction exploiting the centralized training phase. During training SAD allows other agents to not only observe the (exploratory) action chosen, but agents instead also observe the greedy action of their team mates. By combining this simple intuition with an auxiliary task for state prediction and best practices for multi-agent learning, SAD establishes a new state of the art for 2-5 players on the self-play part of the Hanabi challenge.

Similar Papers

Model Based Reinforcement Learning for Atari
Łukasz Kaiser, Mohammad Babaeizadeh, Piotr Miłos, Błażej Osiński, Roy H Campbell, Konrad Czechowski, Dumitru Erhan, Chelsea Finn, Piotr Kozakowski, Sergey Levine, Afroz Mohiuddin, Ryan Sepassi, George Tucker, Henryk Michalewski,
Adversarial Policies: Attacking Deep Reinforcement Learning
Adam Gleave, Michael Dennis, Cody Wild, Neel Kant, Sergey Levine, Stuart Russell,
Optimistic Exploration even with a Pessimistic Initialisation
Tabish Rashid, Bei Peng, Wendelin Boehmer, Shimon Whiteson,