Finding Friend and Foe in Multi-Agent Games

06/05/2019
by   Jack Serrino, et al.
3

Recent breakthroughs in AI for multi-agent games like Go, Poker, and Dota, have seen great strides in recent years. Yet none of these games address the real-life challenge of cooperation in the presence of unknown and uncertain teammates. This challenge is a key game mechanism in hidden role games. Here we develop the DeepRole algorithm, a multi-agent 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. These innovations enable DeepRole to scale to the full Avalon game. 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.

READ FULL TEXT
research
01/17/2020

Algorithms in Multi-Agent Systems: A Holistic Perspective from Reinforcement Learning and Game Theory

Deep reinforcement learning (RL) has achieved outstanding results in rec...
research
05/18/2023

Game Theory with Simulation of Other Players

Game-theoretic interactions with AI agents could differ from traditional...
research
10/11/2022

Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning

No-press Diplomacy is a complex strategy game involving both cooperation...
research
12/07/2021

The Partially Observable Asynchronous Multi-Agent Cooperation Challenge

Multi-agent reinforcement learning (MARL) has received increasing attent...
research
02/20/2019

The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning

Recent years have seen the application of deep reinforcement learning te...
research
10/06/2020

Human-Level Performance in No-Press Diplomacy via Equilibrium Search

Prior AI breakthroughs in complex games have focused on either the purel...
research
02/20/2020

Distributed No-Regret Learning in Multi-Agent Systems

In this tutorial article, we give an overview of new challenges and repr...

Please sign up or login with your details

Forgot password? Click here to reset