arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.02138cs.AI
收藏

多智能体强化学习中内在奖励不可靠的探索

Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning

University of Oxford(牛津大学)

Wendelin Böhmer, Tabish Rashid, Shimon Whiteson

摘要:

本文研究了在多智能体强化学习中使用内在奖励来引导探索。我们讨论了将内在奖励应用于多个协作代理的挑战,并演示了不可靠的奖励如何阻止分散代理学习最优策略。我们解决这个问题,一个新的框架,独立的中央辅助Q学习(ICQL),在分散的代理共享控制和经验重放缓冲区与集中的代理。只有中心化的代理人本质上是奖励,但分散的代理人仍然受益于改进的探索,没有不可靠的激励分散注意力。

英文摘要:

This paper investigates the use of intrinsic reward to guide exploration in multi-agent reinforcement learning. We discuss the challenges in applying intrinsic reward to multiple collaborative agents and demonstrate how unreliable reward can prevent decentralized agents from learning the optimal policy. We address this problem with a novel framework, Independent Centrally-assisted Q-learning (ICQL), in which decentralized agents share control and an experience replay buffer with a centralized agent. Only the centralized agent is intrinsically rewarded, but the decentralized agents still benefit from improved exploration, without the distraction of unreliable incentives.

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。

↑