Finding friend and foe in Avalon with counterfactual regret minimization and deep networks
Author(s)
Serrino, Jack Samuel.
Download1128830334-MIT.pdf (1.012Mb)
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
Joshua Tenenbaum and Max Kleiman-Weiner.
Terms of use
Metadata
Show full item recordAbstract
Recent breakthroughs in AI for multi-agent games like Go, Poker, and Dota, have seen great strides in recent years. Yet none of these AI systems address a key game mechanism in hidden role games. Here we develop the DeepRole algorithm, a multiagent reinforcement learning agent that we test on The Resistance: Avalon, the most popular hidden role game. DeepRole combines counterfactual regret minimization (CFR) with deep value networks trained through self-play. Our algorithm integrates deductive reasoning into vector-form CFR to reason about joint beliefs and deduce partially observable actions. We augment deep value networks with constraints that yield interpretable representations of win probabilities. Empirical game-theoretic methods show that DeepRole outperforms other hand-crafted and learned agents in five-player Avalon. DeepRole played with and against human players on the web in hybrid human-agent teams. We find that DeepRole outperforms human players as both a cooperator and a competitor.
Description
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 39-43).
Date issued
2019Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.