Learning Cooperative Multi-Agent Policies with Partial Reward Decoupling

Abstract

One of the preeminent obstacles to scaling multi-agent reinforcement learning to large numbers of agents is assigning credit to individual agents' actions. In this paper, we address this credit assignment problem with an approach that we call \textit{partial reward decoupling} (PRD), which attempts to decompose large cooperative multi-agent RL problems into decoupled subproblems involving subsets of agents, thereby simplifying credit assignment. We empirically demonstrate that decomposing the RL problem using PRD in an actor-critic algorithm results in lower variance policy gradient estimates, which improves data efficiency, learning stability, and asymptotic performance across a wide array of multi-agent RL tasks, compared to various other actor-critic approaches. Additionally, we relate our approach to counterfactual multi-agent policy gradient (COMA), a state-of-the-art MARL algorithm, and empirically show that our approach outperforms COMA by making better use of information in agents' reward streams, and by enabling recent advances in advantage estimation to be used.

arXiv commentin IEEE Robotics and Automation Letters

References in corpus (8)

• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Trust Region Policy Optimization
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• Dota 2 with Large Scale Deep Reinforcement Learning
• Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
• Distributed Distributional Deterministic Policy Gradients
• Actor-Attention-Critic for Multi-Agent Reinforcement Learning
• Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines