paper-with-me

홈 › Papers

Policy Space Diversity for Non-Transitive Games

2023-06-29 · NeurIPS 2023 11

Policy-Space Response Oracles (PSRO) is an influential algorithm framework for approximating a Nash Equilibrium (NE) in multi-agent non-transitive games. Many previous studies have been trying to promote policy diversity in PSRO. A major weakness in existing diversity metrics is that a more diverse (according to their diversity metrics) population does not necessarily mean (as we proved in the paper) a better approximation to a NE. To alleviate this problem, we propose a new diversity metric, the improvement of which guarantees a better approximation to a NE. Meanwhile, we develop a practical and well-justified method to optimize our diversity metric using only state-action samples. By incorporating our diversity regularization into the best response solving in PSRO, we obtain a new PSRO variant, Policy Space Diversity PSRO (PSD-PSRO). We present the convergence property of PSD-PSRO. Empirically, extensive experiments on various games demonstrate that PSD-PSRO is more effective in producing significantly less exploitable policies than state-of-the-art PSRO variants.

📄 PDF Abstract BibTeX arXiv:2306.16884

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Similar Papers 제목 키워드 기반

Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games

2021-06-09 · Xiangyu Liu, Hangtian Jia, Ying Wen, Yaodong Yang 외

Measuring and promoting policy diversity is critical for solving games with strong non-transitive dynamics where strategic cycles exist, and there is no consistent winner (e.g., Rock-Paper-Scissors). With that in mind, m…

Diversity

Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games

2021-12-01 · NeurIPS 2021 12 · Xiangyu Liu, Hangtian Jia, Ying Wen, Yaodong Yang 외

Measuring and promoting policy diversity is critical for solving games with strong non-transitive dynamics where strategic cycles exist, and there is no consistent winner (e.g., Rock-Paper-Scissors). With that in mind, m…

Diversity

Modelling Behavioural Diversity for Learning in Open-Ended Games

2021-03-14 · Nicolas Perez Nieves, Yaodong Yang, Oliver Slumbers, David Henry Mguni 외

Promoting behavioural diversity is critical for solving games with non-transitive dynamics where strategic cycles exist, and there is no consistent winner (e.g., Rock-Paper-Scissors). Yet, there is a lack of rigorous tre…

DiversityPoint Processes

Ordinal Potential-based Player Rating

2023-06-08 · Nelson Vadori, Rahul Savani

It was recently observed that Elo ratings fail at preserving transitive relations among strategies and therefore cannot correctly extract the transitive component of a game. We provide a characterization of transitive ga…

On the Limitations of Elo: Real-World Games, are Transitive, not Additive

2022-06-21 · Quentin Bertrand, Wojciech Marian Czarnecki, Gauthier Gidel

Real-world competitive games, such as chess, go, or StarCraft II, rely on Elo models to measure the strength of their players. Since these games are not fully transitive, using Elo implicitly assumes they have a strong t…

StarcraftStarcraft II