arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.01264cs.LG
收藏

超越价值函数缺口:改进的情景强化学习的实例相关后悔边界

Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning

Google Research(谷歌研究院);Johns Hopkins University(约翰斯·霍普金斯大学);Courant Institute(库朗研究所)

Christoph Dann, Teodor V. Marinov, Mehryar Mohri, Julian Zimmert

摘要:

我们提供了改进的间隙依赖遗憾界的强化学习有限情节马尔可夫决策过程。与以前的工作相比,我们的界限取决于间隙的替代定义。这些定义是基于这样的认识,即为了实现有利的遗憾,算法不需要学习如何在最优策略未达到的状态下表现最优。我们证明了更严格的乐观算法的遗憾上限,并伴随着他们与新的信息理论的下界为一大类的MDP。我们的研究结果表明,乐观算法不能达到信息论的下限,即使在确定性的MDP,除非有一个唯一的最优策略。

英文摘要:

We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. Compared to prior work, our bounds depend on alternative definitions of gaps. These definitions are based on the insight that, in order to achieve a favorable regret, an algorithm does not need to learn how to behave optimally in states that are not reached by an optimal policy. We prove tighter upper regret bounds for optimistic algorithms and accompany them with new information-theoretic lower bounds for a large class of MDPs. Our results show that optimistic algorithms can not achieve the information-theoretic lower bounds even in deterministic MDPs unless there is a unique optimal policy.

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。

↑