paper-with-me

Papers

Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis

2020-03-16 · Koulik Khamaru, Ashwin Pananjady, Feng Ruan, Martin J. Wainwright, Michael. I. Jordan

We address the problem of policy evaluation in discounted Markov decision processes, and provide instance-dependent guarantees on the $\ell_\infty$-error under a generative model. We establish both asymptotic and non-asymptotic versions of local minimax lower bounds for policy evaluation, thereby providing an instance-dependent baseline by which to compare algorithms. Theory-inspired simulations show that the widely-used temporal difference (TD) algorithm is strictly suboptimal when evaluated in a non-asymptotic setting, even when combined with Polyak-Ruppert iterate averaging. We remedy this issue by introducing and analyzing variance-reduced forms of stochastic approximation, showing that they achieve non-asymptotic, instance-dependent optimality up to logarithmic factors.

📄 PDF Abstract BibTeX arXiv:2003.07337

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Accelerated and instance-optimal policy evaluation with linear function approximation

2021-12-24 · Tianjiao Li, Guanghui Lan, Ashwin Pananjady

We study the problem of policy evaluation with linear function approximation and present efficient and practical algorithms that come with strong optimality guarantees. We begin by proving lower bounds that establish bas…

Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator

2017-12-22 · ICML 2018 7 · Stephen Tu, Benjamin Recht

Reinforcement learning (RL) has been successfully used to solve many continuous control tasks. Despite its impressive results however, fundamental questions regarding the sample complexity of RL on continuous problems re…

continuous-controlContinuous ControlReinforcement LearningReinforcement Learning (RL)

Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential Stability

2023-10-22 · Sergey Samsonov, Daniil Tiapkin, Alexey Naumov, Eric Moulines

In this paper we consider the problem of obtaining sharp bounds for the performance of temporal difference (TD) methods with linear function approximation for policy evaluation in discounted Markov decision processes. We…

Optimal oracle inequalities for solving projected fixed-point equations

2020-12-09 · Wenlong Mou, Ashwin Pananjady, Martin J. Wainwright

Linear fixed point equations in Hilbert spaces arise in a variety of settings, including reinforcement learning, and computational methods for solving differential and integral equations. We study methods that use a coll…

Instance-Dependent Confidence and Early Stopping for Reinforcement Learning

2022-01-21 · Koulik Khamaru, Eric Xia, Martin J. Wainwright, Michael I. Jordan

Various algorithms for reinforcement learning (RL) exhibit dramatic variation in their convergence rates as a function of problem structure. Such problem-dependent behavior is not captured by worst-case analyses and has …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)