跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.19566 · v1

Bellman Residual Bracketing: Resolving the Sample Complexity of Discounted and Average-Reward RL

首次提交 2026-11-15 02:57
版本更新 2026-11-15 02:57
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

We study the sample complexity of the empirical planning or plug-in approach for reinforcement learning (RL) with a generative model. We show the discounted plug-in approach finds an ε\varepsilon-optimal policy with O(SA(1−γ)−3ε−2log⁡(SA/δ))O(SA (1-γ)^{-3} \varepsilon^{-2} \log(SA/δ)) samples, where S,A,γ,δS, A, γ, δ are the state and action sizes, discount factor, and failure probability, respectively. In the average-reward setting, we show that discounted plug-in and direct (undiscounted) plug-in achieve O(SAHε−2log⁡(SA/δ))O(SAH\varepsilon^{-2}\log(SA/δ)) and O(SADε−2log⁡(SA/δ))O(SAD\varepsilon^{-2}\log(SA/δ)) complexities, respectively, where HH upper-bounds the optimal bias span and DD is the diameter. Combining with our lower bounds for nonadaptive generative models, these results resolve the minimax sample complexity of discounted RL and average-reward RL --- in both the span- and diameter-based classes --- up to constant factors. Our main technical contribution is a novel Bellman residual bracketing technique which improves the efficiency of prior absorbing-MDP-based concentration analyses.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-15 02:57 · 最新观测版本

Bellman Residual Bracketing: Resolving the Sample Complexity of Discounted and Average-Reward RL

We study the sample complexity of the empirical planning or plug-in approach for reinforcement learning (RL) with a generative model. We show the discounted plug-in approach finds an ε\varepsilon-optimal policy with O(SA(1−γ)−3ε−2log⁡(SA/δ))O(SA (1-γ)^{-3} \varepsilon^{-2} \log(SA/δ)) samples, where S,A,γ,δS, A, γ, δ are the state and action sizes, discount factor, and failure probability, respectively. In the average-reward setting, we show that discounted plug-in and direct (undiscounted) plug-in achieve O(SAHε−2log⁡(SA/δ))O(SAH\varepsilon^{-2}\log(SA/δ)) and O(SADε−2log⁡(SA/δ))O(SAD\varepsilon^{-2}\log(SA/δ)) complexities, respectively, where HH upper-bounds the optimal bias span and DD is the diameter. Combining with our lower bounds for nonadaptive generative models, these results resolve the minimax sample complexity of discounted RL and average-reward RL --- in both the span- and diameter-based classes --- up to constant factors. Our main technical contribution is a novel Bellman residual bracketing technique which improves the efficiency of prior absorbing-MDP-based concentration analyses.

查看此版本解读 →查看此版本原文 ↗