{"type":"ScholarlyArticle","title":"Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts","authors":[{"name":"Weinan Zhang","slug":"weinan-zhang","given":"Weinan","family":"Zhang","affiliation":""},{"name":"Xihuai Wang","slug":"xihuai-wang","given":"Xihuai","family":"Wang","affiliation":""},{"name":"Jian Shen","slug":"jian-shen","given":"Jian","family":"Shen","affiliation":""},{"name":"Ming Zhou","slug":"ming-zhou","given":"Ming","family":"Zhou","affiliation":""}],"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.","doi":"10.24963/ijcai.2021/466","url":"https://ijcai.org/proceedings/2021/466","pdf":"https://ijcai.org/proceedings/2021/0466.pdf","markdown":"https://ijcai.org/proceedings/2021/466.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/466","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Machine Learning","track":"Main Track","number":466,"pages":{"first":3384,"last":3391},"keywords":["Machine Learning: Deep Reinforcement Learning","Agent-based and Multi-agent Systems: Multi-agent Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}