arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.01182cs.LGcs.MA
收藏

基于学习智能体遗憾界的强化学习迁移方法

Transfer in Reinforcement Learning via Regret Bounds for Learning Agents

Scool team, Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL(Scool团队、里尔大学、Inria、CNRS、里尔中央大学、UMR 9189 CRIStAL)

Adrienne Tuynman, Ronald Ortner

AI总结:

针对多智能体强化学习场景,提出通过遗憾界量化迁移效用的方法,证明智能体共享观测可使总遗憾较独立学习降低√ℵ倍,为观测共享的迁移收益提供了理论界。

摘要:

我们提出了一种多智能体场景下通过遗憾界量化强化学习中迁移效用的方法。考虑数量为ℵ的智能体在同一马尔可夫决策过程中运行,但各智能体可能具备不同的奖励函数,我们针对每个智能体相对于最大化其平均奖励的最优策略所产生的遗憾展开研究。我们证明,当智能体共享观测结果时,所有智能体的总遗憾比每个智能体仅依赖自身收集信息的场景低√ℵ倍。该结果表明,多智能体场景下的遗憾分析能够为迁移学习中观测共享的收益提供理论界。

英文摘要:

We present an approach for the quantification of the usefulness of transfer in reinforcement learning via regret bounds for a multi-agent setting. Considering a number of $\aleph$ agents operating in the same Markov decision process, however possibly with different reward functions, we consider the regret each agent suffers with respect to an optimal policy maximizing her average reward. We show that when the agents share their observations the total regret of all agents is smaller by a factor of $\sqrt{\aleph}$ compared to the case when each agent has to rely on the information collected by herself. This result demonstrates how considering the regret in multi-agent settings can provide theoretical bounds on the benefit of sharing observations in transfer learning.

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。

↑