paper-with-me

홈 › Papers

Regularized Q-Learning with Linear Function Approximation

2024-01-26 · Jiachen Xi, Alfredo Garcia, Petar Momcilovic

Regularized Markov Decision Processes serve as models of sequential decision making under uncertainty wherein the decision maker has limited information processing capacity and/or aversion to model ambiguity. With functional approximation, the convergence properties of learning algorithms for regularized MDPs (e.g. soft Q-learning) are not well understood because the composition of the regularized Bellman operator and a projection onto the span of basis vectors is not a contraction with respect to any norm. In this paper, we consider a bi-level optimization formulation of regularized Q-learning with linear functional approximation. The {\em lower} level optimization problem aims to identify a value function approximation that satisfies Bellman's recursive optimality condition and the {\em upper} level aims to find the projection onto the span of basis vectors. This formulation motivates a single-loop algorithm with finite time convergence guarantees. The algorithm operates on two time-scales: updates to the projection of state-action values are slow' in that they are implemented with a step size that is smaller than the one used for faster' updates of approximate solutions to Bellman's recursive optimality equation. We show that, under certain assumptions, the proposed algorithm converges to a stationary point in the presence of Markovian noise. In addition, we provide a performance guarantee for the policies derived from the proposed algorithm.

📄 PDF Abstract BibTeX arXiv:2401.15196

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making Under UncertaintyQ-LearningSequential Decision Making

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation

2021-06-08 · Semih Cayci, Niao He, R. Srikant

Natural policy gradient (NPG) methods with entropy regularization achieve impressive empirical success in reinforcement learning problems with large state-action spaces. However, their convergence properties and the impa…

Analysis of Regularized Learning in Banach Spaces for Linear-functional Data

2021-09-07 · Qi Ye

This article delves into the study of the theory of regularized learning in Banach spaces for linear-functional data. It encompasses discussions on representer theorems, pseudo-approximation theorems, and convergence the…

An Analysis of State-Relevance Weights and Sampling Distributions on L1-Regularized Approximate Linear Programming Approximation Accuracy

2014-04-16 · Gavin Taylor, Connor Geer, David Piekut

Recent interest in the use of $L_1$ regularization in the use of value function approximation includes Petrik et al.'s introduction of $L_1$-Regularized Approximate Linear Programming (RALP). RALP is unique among $L_1$-r…

Periodic Regularized Q-Learning

2026-02-03 · Hyukjun Yang, Han-Dong Lim, Donghwan Lee arxiv

In reinforcement learning (RL), Q-learning is a fundamental algorithm whose convergence is guaranteed in the tabular setting. However, this convergence guarantee does not hold under linear function approximation. To over…

Reinforcement Learning

On Gaussian approximation for entropy-regularized Q-learning with function approximation

2026-05-17 · Artemy Rubtsov, Rahul Singh, Eric Moulines, Alexey Naumov 외 arxiv

In this paper, we derive rates of convergence in the high-dimensional central limit theorem for Polyak--Ruppert averaged iterates generated by entropy-regularized asynchronous Q-learning with linear function approximatio…