arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.02258cs.LGstat.ML
收藏

具有前瞻信息的强化学习

Reinforcement Learning with Lookahead Information

FairPlay Joint Team, CREST, ENSAE Paris(FairPlay联合团队、CREST、巴黎经济与统计学院)

Nadav Merlis

AI总结:

本文针对智能体在决策前可观察当前状态奖励或转移实现的前瞻信息场景,提出基于经验分布规划的可证明高效强化学习算法,并证明其遗憾紧致且奖励相比无前瞻信息方法线性提升。

摘要:

我们研究一类强化学习(RL)问题,其中智能体在决定采取哪个动作之前,会观察到当前状态下的奖励或转移实现。此类观察在许多应用中可用,包括交易、导航等。当环境已知时,先前的工作表明,这种前瞻信息可以大幅增加收集到的奖励。然而,在特定应用之外,现有用于与未知环境交互的方法并不能很好地适应这些观察。在这项工作中,我们弥补了这一差距,并设计了可证明高效且能够纳入前瞻信息的学习算法。为实现这一目标,我们利用奖励和转移观察的经验分布进行规划,这与仅依赖估计期望的普通方法形成对比。我们证明,我们的算法相对于同样能够获取前瞻信息的基线实现了紧致遗憾——与无法处理前瞻信息的智能体相比,收集到的奖励量呈线性增加。

英文摘要:

We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including transactions, navigation and more. When the environment is known, previous work shows that this lookahead information can drastically increase the collected reward. However, outside of specific applications, existing approaches for interacting with unknown environments are not well-adapted to these observations. In this work, we close this gap and design provably-efficient learning algorithms able to incorporate lookahead information. To achieve this, we perform planning using the empirical distribution of the reward and transition observations, in contrast to vanilla approaches that only rely on estimated expectations. We prove that our algorithms achieve tight regret versus a baseline that also has access to lookahead information - linearly increasing the amount of collected reward compared to agents that cannot handle lookahead information.

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。

↑