Saved in:
Bibliographic Details
Main Authors: Lee, Jongmin, Bravo, Mario, Cominetti, Roberto
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.04477
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911004207611904
author Lee, Jongmin
Bravo, Mario
Cominetti, Roberto
author_facet Lee, Jongmin
Bravo, Mario
Cominetti, Roberto
contents We study a new model-free algorithm to compute $\varepsilon$-optimal policies for average reward Markov decision processes, in the weakly communicating case. Given a generative model, our procedure combines a recursive sampling technique with Halpern's anchored iteration, and computes an $\varepsilon$-optimal policy with sample and time complexity $\widetilde{O}(|\mathcal{S}||\mathcal{A}|\|h^*\|_{\text{sp}}^{2}/\varepsilon^{2})$ both in high probability and in expectation. To our knowledge, this is the best complexity among model-free algorithms, matching the known lower bound up to a factor $\|h^*\|_{\text{sp}}$. Although the complexity bound involves the span seminorm $\|h^*\|_{\text{sp}}$ of the unknown bias vector, the algorithm requires no prior knowledge and implements a stopping rule which guarantees with probability 1 that the procedure terminates in finite time. We also analyze how these techniques can be adapted for discounted MDPs.
format Preprint
id arxiv_https___arxiv_org_abs_2502_04477
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Near-Optimal Sample Complexity for MDPs via Anchoring
Lee, Jongmin
Bravo, Mario
Cominetti, Roberto
Optimization and Control
Data Structures and Algorithms
We study a new model-free algorithm to compute $\varepsilon$-optimal policies for average reward Markov decision processes, in the weakly communicating case. Given a generative model, our procedure combines a recursive sampling technique with Halpern's anchored iteration, and computes an $\varepsilon$-optimal policy with sample and time complexity $\widetilde{O}(|\mathcal{S}||\mathcal{A}|\|h^*\|_{\text{sp}}^{2}/\varepsilon^{2})$ both in high probability and in expectation. To our knowledge, this is the best complexity among model-free algorithms, matching the known lower bound up to a factor $\|h^*\|_{\text{sp}}$. Although the complexity bound involves the span seminorm $\|h^*\|_{\text{sp}}$ of the unknown bias vector, the algorithm requires no prior knowledge and implements a stopping rule which guarantees with probability 1 that the procedure terminates in finite time. We also analyze how these techniques can be adapted for discounted MDPs.
title Near-Optimal Sample Complexity for MDPs via Anchoring
topic Optimization and Control
Data Structures and Algorithms
url https://arxiv.org/abs/2502.04477