PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
Authors:
- Pengyi LiPLPengyi Li
- Hongyao TangHTHongyao Tang
- Tianpei YangTYTianpei Yang
- Xiaotian HaoXHXiaotian Hao
- Tong SangTSTong Sang
- Yan ZhengYZYan Zheng
- Jianye HaoJHJianye Hao
- Matthew E. TaylorMTMatthew E. Taylor
- Wenyuan TaoWTWenyuan Tao
- Zhen WangZWZhen Wang
- Fazl BarezFBFazl Barez
Preprint
Abstract
Learning to collaborate is critical in Multi-Agent Reinforcement Learning (MARL). Previous works promote collaboration by maximizing the correlation of agents' behaviors, which is typically characterized by Mutual Information (MI) in different forms. However, we reveal sub-optimal collaborative behaviors also emerge with strong correlations, and simply maximizing the MI can, surprisingly, hinder the learning towards better collaboration. To address this issue, we propose a novel MARL framework, called Progressive Mutual Information Collaboration (PMIC), for more effective MI-driven collaboration. PMIC uses a new collaboration criterion measured by the MI between global states and joint actions. Based on this criterion, the key idea of PMIC is maximizing the MI associated with superior collaborative behaviors and minimizing the MI associated with inferior ones. The two MI objectives play complementary roles by facilitating better collaborations while avoiding falling into sub-optimal ones. Experiments on a wide range of MARL benchmarks show the superior performance of PMIC compared with other algorithms.Keywords
All Related Versions
This publication has 3 references indexed in Scilit:
- A Deeper Understanding of State-Based Critics in Multi-Agent Reinforcement LearningProceedings of the AAAI Conference on Artificial Intelligence, 2022
- A survey and critique of multiagent deep reinforcement learningAutonomous Agents and Multi-Agent Systems, 2019
- A Concise Introduction to Decentralized POMDPs2016