跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.23596 · v1

Efficient Variance-Aware Reinforcement Learning in Time-Inhomogeneous Linear MDPs

首次提交 2026-11-18 06:51
版本更新 2026-11-18 06:51
雷达观测 2026-11-19 19:08
arXiv ↗PDF ↗

摘要

We study variance-dependent reinforcement learning in episodic time-inhomogeneous linear Markov decision processes (MDPs) with feature dimension dd, horizon HH, and KK episodes. While recent works have established variance-dependent regret with O~(1)\tilde{O}(1) deterministic-regime overhead for linear mixture MDPs (Zhao et al., 2023) and worst-case nearly minimax optimal regret O~(dH3K+d7H8)\tilde{O}(d\sqrt{H^3 K} + d^7 H^8) for linear MDPs (He et al., 2023),, existing variance-aware analyses for linear MDPs (Li and Sun, 2023; Huang et al., 2023) rely on a coarse concentration step whose resulting regret guarantees retain a polynomial O~(K1/4)\tilde{O}(K^{1/4}) additive term even in deterministic environments. We propose VA-LSVI-UCB++, a computationally efficient algorithm that achieves the variance-dependent regret bound O~(dHmin⁡{VarK∗,VarKπ}+d5H4)\tilde{O}(d\sqrt{H\min\{\mathrm{Var}_K^*,\mathrm{Var}_K^π\}}+d^5H^4), where VarK∗\mathrm{Var}_K^* and VarKπ\mathrm{Var}_K^π denote the cumulative conditional variances of the optimal value function and the played policies' value functions along the realized trajectory. Our result adapts to the minimum of the two realized trajectory variances, recovers the worst-case minimax optimal leading term O~(dH3K)\tilde{O}(d\sqrt{H^3 K}), and collapses to O~(d5H4)\tilde{O}(d^5 H^4) in deterministic environments, free of polynomial-in-KK dependency. At the core of our analysis is a simultaneous three-way reference-advantage decomposition for the optimistic, pessimistic, and squared value function estimators coupled with variance self-bounding and Freedman-type value-difference arguments, which tightens the pessimistic and second-moment confidence radii by a factor of O~(dH)\tilde{O}(d H) and removes the inverse-variance-floor blowup.

作者备注:38 pages, 2 tables

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 · 2026-11-18 06:51 · 最新观测版本

Efficient Variance-Aware Reinforcement Learning in Time-Inhomogeneous Linear MDPs

We study variance-dependent reinforcement learning in episodic time-inhomogeneous linear Markov decision processes (MDPs) with feature dimension dd, horizon HH, and KK episodes. While recent works have established variance-dependent regret with O~(1)\tilde{O}(1) deterministic-regime overhead for linear mixture MDPs (Zhao et al., 2023) and worst-case nearly minimax optimal regret O~(dH3K+d7H8)\tilde{O}(d\sqrt{H^3 K} + d^7 H^8) for linear MDPs (He et al., 2023),, existing variance-aware analyses for linear MDPs (Li and Sun, 2023; Huang et al., 2023) rely on a coarse concentration step whose resulting regret guarantees retain a polynomial O~(K1/4)\tilde{O}(K^{1/4}) additive term even in deterministic environments. We propose VA-LSVI-UCB++, a computationally efficient algorithm that achieves the variance-dependent regret bound O~(dHmin⁡{VarK∗,VarKπ}+d5H4)\tilde{O}(d\sqrt{H\min\{\mathrm{Var}_K^*,\mathrm{Var}_K^π\}}+d^5H^4), where VarK∗\mathrm{Var}_K^* and VarKπ\mathrm{Var}_K^π denote the cumulative conditional variances of the optimal value function and the played policies' value functions along the realized trajectory. Our result adapts to the minimum of the two realized trajectory variances, recovers the worst-case minimax optimal leading term O~(dH3K)\tilde{O}(d\sqrt{H^3 K}), and collapses to O~(d5H4)\tilde{O}(d^5 H^4) in deterministic environments, free of polynomial-in-KK dependency. At the core of our analysis is a simultaneous three-way reference-advantage decomposition for the optimistic, pessimistic, and squared value function estimators coupled with variance self-bounding and Freedman-type value-difference arguments, which tightens the pessimistic and second-moment confidence radii by a factor of O~(dH)\tilde{O}(d H) and removes the inverse-variance-floor blowup.

查看此版本解读 →查看此版本原文 ↗