跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.17603 · v1

Offline KL-Regularized Reinforcement Learning with Stochastic Transitions

首次提交 2026-11-13 07:53
版本更新 2026-11-13 07:53
雷达观测 2026-11-17 04:58
arXiv ↗PDF ↗

摘要

KL-regularized reinforcement learning is the objective behind RL fine-tuning of language models, and its data are often collected by the reference policy itself. However, beyond bandits and deterministic transitions, little is known about how much offline data it needs. In this work, we study finite discounted Markov decision processes with unknown stochastic transitions, KK state-action pairs and effective horizon HH. For data that cover the regularized optimum with concentrability C≥4C\geq 4, every estimator needs Ω(KCH3/(εmax⁡{ε,β}))Ω(KCH^3/(ε\max\{ε,β\})) samples on some instances when εε is small, where ββ is the temperature. Under a fixed design, pessimistic soft value iteration with a variance-aware penalty attains this rate with high probability, up to logarithmic factors, when β≥1.4Hβ\geq 1.4H. When the data come from the reference policy itself, we show that it covers the optimum up to a power law whose exponent grows as H/βH/β; in the same temperature range, this power law alone gives the estimator a sample complexity polynomial in 1/ε1/ε, with no coverage assumption. For β≥Hβ\geq H the power can also increase the sample size needed by a factor polynomial in 1/ε1/ε. Finally, the plug-in estimator, which is minimax optimal with a generative model, can fail on reference data at small temperatures when many actions are rarely seen, while the pessimistic estimator does not.

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 · 2026-11-13 07:53 · 最新观测版本

Offline KL-Regularized Reinforcement Learning with Stochastic Transitions

KL-regularized reinforcement learning is the objective behind RL fine-tuning of language models, and its data are often collected by the reference policy itself. However, beyond bandits and deterministic transitions, little is known about how much offline data it needs. In this work, we study finite discounted Markov decision processes with unknown stochastic transitions, KK state-action pairs and effective horizon HH. For data that cover the regularized optimum with concentrability C≥4C\geq 4, every estimator needs Ω(KCH3/(εmax⁡{ε,β}))Ω(KCH^3/(ε\max\{ε,β\})) samples on some instances when εε is small, where ββ is the temperature. Under a fixed design, pessimistic soft value iteration with a variance-aware penalty attains this rate with high probability, up to logarithmic factors, when β≥1.4Hβ\geq 1.4H. When the data come from the reference policy itself, we show that it covers the optimum up to a power law whose exponent grows as H/βH/β; in the same temperature range, this power law alone gives the estimator a sample complexity polynomial in 1/ε1/ε, with no coverage assumption. For β≥Hβ\geq H the power can also increase the sample size needed by a factor polynomial in 1/ε1/ε. Finally, the plug-in estimator, which is minimax optimal with a generative model, can fail on reference data at small temperatures when many actions are rarely seen, while the pessimistic estimator does not.

查看此版本解读 →查看此版本原文 ↗