arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.09435cs.MAcs.AIcs.GTcs.LG
收藏

超越零和的智能体多智能体训练:基于关联均衡元求解器

Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers

DeepMind(深度思维);University College London(伦敦大学学院);Université Gustave Eiffel(古斯塔夫·埃菲尔大学)

Luke Marris, Paul Muller, Marc Lanctot, Karl Tuyls, Thore Graepel

AI总结:

提出JPSRO算法,用于n人一般和扩展型博弈中的智能体训练,证明收敛到均衡,并引入最大基尼关联均衡(MGCE)作为高效的关联均衡元求解器,实验验证其收敛性。

摘要:

两人常数和博弈在文献中已有充分研究,但在此设定之外的进展有限。我们提出联合策略空间响应预言机(JPSRO),一种用于在n人一般和扩展型博弈中训练智能体的算法,并证明其可收敛到均衡。我们进一步提出关联均衡(CE)作为有前景的元求解器,并提出一种新颖的求解概念——最大基尼关联均衡(MGCE),这是一族有原则且计算高效的解决方案,用于解决关联均衡选择问题。我们使用CE元求解器进行多项JPSRO实验,并展示了在n人一般和博弈上的收敛性。

英文摘要:

Two-player, constant-sum games are well studied in the literature, but there has been limited progress outside of this setting. We propose Joint Policy-Space Response Oracles (JPSRO), an algorithm for training agents in n-player, general-sum extensive form games, which provably converges to an equilibrium. We further suggest correlated equilibria (CE) as promising meta-solvers, and propose a novel solution concept Maximum Gini Correlated Equilibrium (MGCE), a principled and computationally efficient family of solutions for solving the correlated equilibrium selection problem. We conduct several experiments using CE meta-solvers for JPSRO and demonstrate convergence on n-player, general-sum games.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑