Approximations and Learning for Continuous State and Action MDPs under Average Cost Criteria

Дата публикации: 17-08-2026 20:26:00

In this paper, for Markov Decision Processes (MDPs) with standard Borel spaces, (i) we first provide a discretization based approximation method for MDPs with continuous spaces under average cost criteria, and provide error bounds for approximations when the dynamics are only weakly continuous (for asymptotic convergence of errors as the grid sizes vanish) or Wasserstein continuous (with a rate in approximation as the grid sizes vanish) under certain ergodicity assumptions. In particular, we relax the total variation condition given in prior work to weak continuity or Wasserstein continuity. (ii) We provide synchronous and asynchronous (quantized) Q-learning algorithms for continuous spaces via quantization (where the quantized state is taken to be the actual state in corresponding Q-learning algorithms presented in the paper), and establish their convergence. (iii) We finally show that the convergence is to the optimal Q values of a finite approximate model constructed via quantization, which implies near optimality of the arrived solution.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	A Two-Timescale Primal-Dual Framework for Reinforcement Learning via Online Dual Variable Guidance	0	13.12	17-08-2026
2	Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features	0	4.2	17-08-2026
3	A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization	0	9.82	17-08-2026
4	Statistical Learning Theory for Neural Operators	0	10.21	17-08-2026
5	Convergence of Noise-Free Sampling Algorithms with Regularized Wasserstein Proximals	0	8.02	17-08-2026
6	Graph-based Clustering Revisited: A Relaxation of Kernel k-Means Perspective	0	10.94	17-08-2026
7	A Symplectic Analysis of Alternating Mirror Descent	0	5.7	17-08-2026
8	Accelerating Constrained Sampling: A Large Deviations Approach	0	7.94	17-08-2026
9	Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent	0	6.66	17-08-2026
10	Near-optimal Delta-convex Estimation of Lipschitz Functions	0	9.71	17-08-2026

Классификация: . Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 4.1. Источник: jmlr.org.