arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.09745cs.LG
收藏

分散确定性多智能体强化学习

Decentralized Deterministic Multi-Agent Reinforcement Learning

Ecole Polytechnique(巴黎综合理工学院);AStar(新加坡科技研究局);IBM Research(IBM研究院)

Antoine Grosnit, Desmond Cai, Laura Wynter

摘要:

[Zhang,ICML 2018]为多智能体强化学习(MARL)提供了第一个分散的演员-评论家算法,该算法提供了收敛保证。在这项工作中,政策是随机的,并定义在有限的行动空间。我们扩展了这些结果,提供了一个可证明收敛的分散的演员-评论家算法学习确定性政策的连续动作空间。确定性策略在现实环境中很重要。为了解决确定性策略中缺乏探索的问题,我们考虑了关闭策略和打开策略设置。我们提供了一个本地的确定性策略梯度,分散的确定性演员批评算法和线性近似价值函数的收敛保证的表达。这项工作将有助于在高维动作空间中实现去中心化的MARL,并为MARL的更广泛使用铺平道路。

英文摘要:

[Zhang, ICML 2018] provided the first decentralized actor-critic algorithm for multi-agent reinforcement learning (MARL) that offers convergence guarantees. In that work, policies are stochastic and are defined on finite action spaces. We extend those results to offer a provably-convergent decentralized actor-critic algorithm for learning deterministic policies on continuous action spaces. Deterministic policies are important in real-world settings. To handle the lack of exploration inherent in deterministic policies, we consider both off-policy and on-policy settings. We provide the expression of a local deterministic policy gradient, decentralized deterministic actor-critic algorithms and convergence guarantees for linearly-approximated value functions. This work will help enable decentralized MARL in high-dimensional action spaces and pave the way for more widespread use of MARL.

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。

↑