arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.13639cs.LGmath.OCstat.ML
收藏

在最小假设下实现单循环Actor-Critic的ε^{-2}样本复杂度

Achieving $ε^{-2}$ Sample Complexity for Single-Loop Actor-Critic under Minimal Assumptions

IISc(印度斯里尼瓦西大学);Purdue IE(普渡大学工业工程学院)

Ishaq Hamza, Zaiwei Chen

AI总结:

本文在最小假设下,通过单循环单时间尺度实现和广泛策略更新类,证明了首次ε^{-2}样本复杂度保证,找到ε-最优策略,与现有文献不同,无需嵌套循环或强假设。

摘要:

在本文中,我们建立了强化学习中off-policy actor-critic方法的最后迭代收敛速率。特别是,在单循环、单时间尺度实现和广泛策略更新类(包括近似策略迭代和自然策略梯度方法)下,我们证明了在最小假设(即存在诱导不可约马尔可夫链的策略)下,首次~O(ε^{-2})样本复杂度保证,以找到ε-最优策略。这与现有文献形成鲜明对比,其中~O(ε^{-2})样本复杂度仅通过嵌套循环更新或强、算法依赖的假设(如均匀混合和均匀探索)实现。技术上,为了解决单循环实现带来的耦合更新方程和可能的无界迭代,我们的分析基于耦合Lyapunov漂移框架。具体而言,我们建立了actor的几何收敛速率和critic的~O(1/T)收敛速率,并通过交叉支配性质结合两个Lyapunov漂移不等式。我们相信这个分析框架具有独立兴趣,可能适用于其他具有无界迭代的耦合迭代算法。

英文摘要:

In this paper, we establish last-iterate convergence rates for off-policy actor--critic methods in reinforcement learning. In particular, under a single-loop, single-timescale implementation and a broad class of policy updates, including approximate policy iteration and natural policy gradient methods, we prove the first $\tilde{\mathcal{O}}(ε^{-2})$ sample complexity guarantee for finding an $ε$-optimal policy under minimal assumptions, namely, the existence of a policy that induces an irreducible Markov chain. This stands in stark contrast to the existing literature, where an $\tilde{\mathcal{O}}(ε^{-2})$ sample complexity is achieved only through nested-loop updates and/or under strong, algorithm-dependent assumptions on the policies, such as uniform mixing and uniform exploration. Technically, to address the challenges posed by the coupled update equations arising from the single-loop implementation, as well as the potentially unbounded iterates induced by off-policy learning, our analysis is based on a coupled Lyapunov drift framework. Specifically, we establish a geometric convergence rate for the actor and an $\tilde{\mathcal{O}}(1/T)$ convergence rate for the critic, and combine the two Lyapunov drift inequalities through a cross-domination property. We believe this analytical framework is of independent interest and may be applicable to other coupled iterative algorithms with unbounded

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。

↑