arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.01547cs.AI
收藏

用于稳定平均场博弈的策略更新正则化

Regularization of the policy updates for stabilizing Mean Field Games

Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Technology Innovation Institute(技术创新研究所)

Talal Algumaei, Ruben Solozabal, Reda Alami, Hakim Hacid, Merouane Debbah, Martin Takac

AI总结:

本文针对大规模多智能体强化学习中的非平稳性问题,提出基于平均场策略近端更新的MF-PPO算法,以替代传统平滑技术,并在OpenSpiel框架中验证了其稳定学习的有效性。

摘要:

本文研究非合作多智能体强化学习(MARL),其中多个智能体在同一环境中交互,目标是最大化各自的回报。当智能体数量扩大时,由于大量智能体引入的非平稳性,会带来挑战。为了解决这一问题,平均场博弈(MFG)依靠对称性和同质性假设来近似具有非常大群体的博弈。近年来,深度强化学习已被用于将MFG扩展到具有更多状态数量的博弈中。当前方法依赖于平滑技术,例如对q值或平均场分布的更新进行平均。本文提出了一种不同的方法来稳定学习,该方法基于对平均场策略的近端更新。我们将算法命名为平均场近端策略优化(MF-PPO),并在OpenSpiel框架中通过实验证明了该方法的有效性。

英文摘要:

This work studies non-cooperative Multi-Agent Reinforcement Learning (MARL) where multiple agents interact in the same environment and whose goal is to maximize the individual returns. Challenges arise when scaling up the number of agents due to the resultant non-stationarity that the many agents introduce. In order to address this issue, Mean Field Games (MFG) rely on the symmetry and homogeneity assumptions to approximate games with very large populations. Recently, deep Reinforcement Learning has been used to scale MFG to games with larger number of states. Current methods rely on smoothing techniques such as averaging the q-values or the updates on the mean-field distribution. This work presents a different approach to stabilize the learning based on proximal updates on the mean-field policy. We name our algorithm Mean Field Proximal Policy Optimization (MF-PPO), and we empirically show the effectiveness of our method in the OpenSpiel framework.

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。

↑