arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.13085cs.AIcs.LGcs.MA
收藏

多智能体强化学习中的并行知识转移

Parallel Knowledge Transfer in Multi-Agent Reinforcement Learning

Carnegie Mellon University(卡内基梅隆大学);Sun Yat-sen University(中山大学)

Yongyuan Liang, Bangwei Li

摘要:

多智能体强化学习是一个标准的框架,用于建模应用于现实世界的场景中的多智能体交互。受人类群体经验共享的启发,学习知识在智能体之间的并行重用可以潜在地促进团队学习性能,特别是在多任务环境中。当所有智能体与环境交互并同时学习时,每个独立的智能体如何有选择地从其他智能体的行为知识中学习是我们需要解决的问题。本文提出了一种新的MARL知识转移框架PAT(Parallel Attentional Transfer)。在PAT中我们设计了两种行动模式,学生模式和自主学习模式。在我们的方法中,每个代理都训练了一个分散的学生演员-评论家,以确定其在每个时间步的表演模式。当Agent对环境不熟悉时,学生模式中的共享注意力机制有效地从其他Agent那里选择学习知识来决定Agent的行动。PAT优于国家的最先进的经验评估结果对以前的建议方法。我们的方法不仅显着提高团队的学习率和整体性能,但也是灵活的和可移植的,适用于各种多智能体系统。

英文摘要:

Multi-agent reinforcement learning is a standard framework for modeling multi-agent interactions applied in real-world scenarios. Inspired by experience sharing in human groups, learning knowledge parallel reusing between agents can potentially promote team learning performance, especially in multi-task environments. When all agents interact with the environment and learn simultaneously, how each independent agent selectively learns from other agents' behavior knowledge is a problem that we need to solve. This paper proposes a novel knowledge transfer framework in MARL, PAT (Parallel Attentional Transfer). We design two acting modes in PAT, student mode and self-learning mode. Each agent in our approach trains a decentralized student actor-critic to determine its acting mode at each time step. When agents are unfamiliar with the environment, the shared attention mechanism in student mode effectively selects learning knowledge from other agents to decide agents' actions. PAT outperforms state-of-the-art empirical evaluation results against the prior advising approaches. Our approach not only significantly improves team learning rate and global performance, but also is flexible and transferable to be applied in various multi-agent systems.

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。

↑