A Distributional Perspective on Value Function Factorization Methods for Multi-Agent Reinforcement Learning

Wei-Fang Sun (National Tsing Hua University), Cheng-Kuang Lee (NVIDIA Corporation), Chun-Yi Lee (National Tsing Hua University)

Abstract

Distributional reinforcement learning (RL) provides beneficial impacts for the single-agent domain. However, distributional RL methods are not directly compatible with value function factorization methods for multi-agent reinforcement learning. This work provides a distributional perspective on value function factorization, offering a solution for bridging the gap between distributional RL and value function factorization methods.