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 2003.10185eess.SYcs.SY
收藏

具有共享动作的分散式多智能体强化学习

Decentralized multi-agent reinforcement learning with shared actions

Rajesh K Mishra, Deepanshu Vasal, Sriram Vishwanath

摘要:

在本文中,我们提出了一种新的无模型的强化学习算法来计算最优策略的多智能体系统与$N$合作代理,每个代理私人观察自己的私人类型和公开观察对方的行动。目标是最大化他们的集体回报。该问题属于广义的部分信息分散控制问题。我们使用的共同代理人的方法,其中一些虚构的共同代理人挑选最佳政策的基础上,对代理人的当前状态的信念。这些信念根据每个代理当前的信念和动作历史单独更新。在没有系统动力学知识的情况下更新信念状态是一个挑战。在本文中,我们采用粒子过滤器称为自助过滤器分布在代理更新的信念。我们提供了一个无模型的强化学习(RL)方法,这个多代理部分可观察马尔可夫决策过程使用粒子滤波器和采样轨迹估计代理的最优策略。我们展示了我们的结果的帮助下,智能电网应用程序,用户努力降低集体成本的电力在电网中的所有代理。最后,我们比较了RL算法的模型和无模型实现的性能,建立了粒子滤波(PF)方法的有效性。

英文摘要:

In this paper, we propose a novel model-free reinforcement learning algorithm to compute the optimal policies for a multi-agent system with $N$ cooperative agents where each agent privately observes it's own private type and publicly observes each others' actions. The goal is to maximize their collective reward. The problem belongs to the broad class of decentralized control problems with partial information. We use the common agent approach wherein some fictitious common agent picks the best policy based on a belief on the current states of the agents. These beliefs are updated individually for each agent from their current belief and action histories. Belief state updates without the knowledge of system dynamics is a challenge. In this paper, we employ particle filters called the bootstrap filter distributively across agents to update the belief. We provide a model-free reinforcement learning (RL) method for this multi-agent partially observable Markov decision processes using the particle filter and sampled trajectories to estimate the optimal policies for the agents. We showcase our results with the help of a smartgrid application where the users strive to reduce collective cost of power for all the agents in the grid. Finally, we compare the performances for model and model-free implementation of the RL algorithm establishing the effectiveness of particle filter (pf) method.

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。

↑