arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.11517cs.AI
收藏

多智能体博弈深度强化学习中通过策略信息正则化实现巩固

Consolidation via Policy Information Regularization in Deep RL for Multi-Agent Games

Rensselaer Polytechnic Institute(伦斯勒理工学院);IBM Research AI(IBM研究院人工智能实验室)

Tailia Malloy, Tim Klinger, Miao Liu, Matthew Riemer, Gerald Tesauro, Chris R. Sims

AI总结:

针对多智能体环境因其他智能体策略变化而产生的非平稳性,本文提出 Capacity-Limited MADDPG,通过信息论约束限制策略复杂度,提升合作与竞争任务中的学习性能。

摘要:

本文在多智能体深度确定性策略梯度(MADDPG)强化学习算法中,引入了一种针对所学策略复杂度的信息论约束。此前在连续控制实验中采用相关方法的研究表明,该方法倾向于学习对环境动态变化更具鲁棒性的策略。多智能体博弈场景天然需要这种鲁棒性,因为其他智能体的策略在整个学习过程中会不断变化,从而引入非平稳环境。为此,本文将持续学习中的近期方法与我们称为 Capacity-Limited MADDPG(容量受限 MADDPG)的方法进行比较。在多智能体合作与竞争任务中的实验结果表明,容量受限方法是提升这些环境中学习性能的良好候选方案。

英文摘要:

This paper introduces an information-theoretic constraint on learned policy complexity in the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm. Previous research with a related approach in continuous control experiments suggests that this method favors learning policies that are more robust to changing environment dynamics. The multi-agent game setting naturally requires this type of robustness, as other agents' policies change throughout learning, introducing a nonstationary environment. For this reason, recent methods in continual learning are compared to our approach, termed Capacity-Limited MADDPG. Results from experimentation in multi-agent cooperative and competitive tasks demonstrate that the capacity-limited approach is a good candidate for improving learning performance in these environments.

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。

↑