Proceedings

Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts

Weinan Zhang, Xihuai Wang, Jian Shen, Ming Zhou

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 3384-3391.

https://doi.org/10.24963/ijcai.2021/466

Keywords

  • Machine Learning: Deep Reinforcement Learning
  • Agent-based and Multi-agent Systems: Multi-agent Learning

Abstract

This paper investigates the model-based methods in multi-agent reinforcement learning (MARL). We specify the dynamics sample complexity and the opponent sample complexity in MARL, and conduct a theoretic analysis of return discrepancy upper bound. To reduce the upper bound with the intention of low sample complexity during the whole learning process, we propose a novel decentralized model-based MARL method, named Adaptive Opponent-wise Rollout Policy Optimization (AORPO). In AORPO, each agent builds its multi-agent environment model, consisting of a dynamics model and multiple opponent models, and trains its policy with the adaptive opponent-wise rollout. We further prove the theoretic convergence of AORPO under reasonable assumptions. Empirical experiments on competitive and cooperative tasks demonstrate that AORPO can achieve improved sample efficiency with comparable asymptotic performance over the compared MARL methods.

Weinan Zhang, Xihuai Wang, Jian Shen, and Ming Zhou. 2021. Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 3384–3391. https://doi.org/10.24963/ijcai.2021/466
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards