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 1909.05232cs.MAcs.AI
收藏

多智能体强化学习中的记忆机制研究

On Memory Mechanism in Multi-Agent Reinforcement Learning

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);US Army Research Lab(美国陆军研究实验室)

Yilun Zhou, Derrik E. Asher, Nicholas R. Waytowich, Julie A. Shah

摘要:

多智能体强化学习(MARL)通过引入额外的智能体和(潜在的)环境的部分可观测性来扩展(单智能体)强化学习(RL)。因此,用于解决MARL问题的算法结合了传统RL方法之外的各种扩展,例如合作代理之间的学习通信协议,该协议能够在竞争环境中交换私人信息或对对手进行自适应建模。一种流行的算法构造是记忆机制,这样代理的决策不仅取决于当前状态,还取决于观察到的状态和动作的历史。在本文中,我们研究了如何记忆机制可以是有用的环境中具有不同的属性,如可观察性,内在性和存在的通信信道。使用以前的工作和新的实验,我们表明,记忆机制是有帮助的,当学习代理需要模拟其他代理和/或通信时,以某种方式受到限制,但是,我们必须谨慎的代理实现有效的记忆通过其他手段。

英文摘要:

Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solving MARL problems incorporate various extensions beyond traditional RL methods, such as a learned communication protocol between cooperative agents that enables exchange of private information or adaptive modeling of opponents in competitive settings. One popular algorithmic construct is a memory mechanism such that an agent's decisions can depend not only upon the current state but also upon the history of observed states and actions. In this paper, we study how a memory mechanism can be useful in environments with different properties, such as observability, internality and presence of a communication channel. Using both prior work and new experiments, we show that a memory mechanism is helpful when learning agents need to model other agents and/or when communication is constrained in some way; however we must to be cautious of agents achieving effective memoryfulness through other means.

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。

↑