arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.01795cs.GTcs.CCcs.LGcs.MA
收藏

一般和随机对策马氏完美均衡计算的复杂性

On the Complexity of Computing Markov Perfect Equilibrium in General-Sum Stochastic Games

Center on Frontiers of Computing Studies(计算研究前沿中心);Peking University(北京大学);Huawei R&D UK(华为英国研发中心);University College London(伦敦大学学院);Institute for AI, Peking University(北京大学人工智能研究院)

Xiaotie Deng, Ningyuan Li, David Mguni, Jun Wang, Yaodong Yang

摘要:

类似于马尔可夫决策过程在强化学习中的作用,随机游戏(SG)为多智能体强化学习(MARL)和顺序智能体交互的研究奠定了基础。本文证明了在指数精度下计算有限状态折扣随机博弈的近似马尔可夫完美均衡是\textbf{PPAD} -完全的。我们采用了一个函数与多项式有界的描述在战略空间转换MPE计算到一个不动点问题,即使随机游戏可能需要一个指数数量的纯策略,在国家的数量,为每个代理。完整性结果遵循将定点问题简化为{ \sc End of the Line}。我们的研究结果表明,在SG中发现MPE极不可能是\textbf{NP} -困难的,除非\textbf{NP} = \textbf{co-NP}。我们的工作为MARL研究提供了信心,研究MPE计算一般和SG和开发富有成效的算法,目前零和SG。

英文摘要:

Similar to the role of Markov decision processes in reinforcement learning, Stochastic Games (SGs) lay the foundation for the study of multi-agent reinforcement learning (MARL) and sequential agent interactions. In this paper, we derive that computing an approximate Markov Perfect Equilibrium (MPE) in a finite-state discounted Stochastic Game within the exponential precision is \textbf{PPAD}-complete. We adopt a function with a polynomially bounded description in the strategy space to convert the MPE computation to a fixed-point problem, even though the stochastic game may demand an exponential number of pure strategies, in the number of states, for each agent. The completeness result follows the reduction of the fixed-point problem to {\sc End of the Line}. Our results indicate that finding an MPE in SGs is highly unlikely to be \textbf{NP}-hard unless \textbf{NP}=\textbf{co-NP}. Our work offers confidence for MARL research to study MPE computation on general-sum SGs and to develop fruitful algorithms as currently on zero-sum SGs.

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。

↑