Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916958958518272 |
|---|---|
| author | Wei, Yukuan Li, Xudong Yang, Lin F. |
| author_facet | Wei, Yukuan Li, Xudong Yang, Lin F. |
| contents | Recent advances have significantly improved our understanding of the sample complexity of learning in average-reward Markov decision processes (AMDPs) under the generative model. However, much less is known about the constrained average-reward MDP (CAMDP), where policies must satisfy long-run average constraints. In this work, we address this gap by studying the sample complexity of learning an $ε$-optimal policy in CAMDPs under a generative model. We propose a model-based algorithm that operates under two settings: (i) relaxed feasibility, which allows small constraint violations, and (ii) strict feasibility, where the output policy satisfies the constraint. We show that our algorithm achieves sample complexities of $\tilde{O}\left(\frac{S A (B+H)}{ ε^2}\right)$ and $\tilde{O} \left(\frac{S A (B+H)}{ε^2 ζ^2} \right)$ under the relaxed and strict feasibility settings, respectively. Here, $ζ$ is the Slater constant indicating the size of the feasible region, $H$ is the span bound of the bias function, and $B$ is the transient time bound. Moreover, a matching lower bound of $\tildeΩ\left(\frac{S A (B+H)}{ ε^2ζ^2}\right)$ for the strict feasibility case is established, thus providing the first minimax-optimal bounds for CAMDPs. Our results close the theoretical gap in understanding the complexity of constrained average-reward MDPs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16586 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs Wei, Yukuan Li, Xudong Yang, Lin F. Machine Learning Recent advances have significantly improved our understanding of the sample complexity of learning in average-reward Markov decision processes (AMDPs) under the generative model. However, much less is known about the constrained average-reward MDP (CAMDP), where policies must satisfy long-run average constraints. In this work, we address this gap by studying the sample complexity of learning an $ε$-optimal policy in CAMDPs under a generative model. We propose a model-based algorithm that operates under two settings: (i) relaxed feasibility, which allows small constraint violations, and (ii) strict feasibility, where the output policy satisfies the constraint. We show that our algorithm achieves sample complexities of $\tilde{O}\left(\frac{S A (B+H)}{ ε^2}\right)$ and $\tilde{O} \left(\frac{S A (B+H)}{ε^2 ζ^2} \right)$ under the relaxed and strict feasibility settings, respectively. Here, $ζ$ is the Slater constant indicating the size of the feasible region, $H$ is the span bound of the bias function, and $B$ is the transient time bound. Moreover, a matching lower bound of $\tildeΩ\left(\frac{S A (B+H)}{ ε^2ζ^2}\right)$ for the strict feasibility case is established, thus providing the first minimax-optimal bounds for CAMDPs. Our results close the theoretical gap in understanding the complexity of constrained average-reward MDPs. |
| title | Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.16586 |