Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.18964 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910147808329728 |
|---|---|
| author | Liu, Xingtu |
| author_facet | Liu, Xingtu |
| contents | This paper establishes central limit theorems for Polyak-Ruppert averaged Q-learning under asynchronous updates. We prove a non-asymptotic central limit theorem, where the convergence rate in Wasserstein distance explicitly reflects the dependence on the number of iterations, state-action space size, the discount factor, and the quality of exploration. In addition, we derive a functional central limit theorem, showing that the partial-sum process converges weakly to a Brownian motion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18964 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Central Limit Theorems for Asynchronous Averaged Q-Learning Liu, Xingtu Machine Learning Optimization and Control This paper establishes central limit theorems for Polyak-Ruppert averaged Q-learning under asynchronous updates. We prove a non-asymptotic central limit theorem, where the convergence rate in Wasserstein distance explicitly reflects the dependence on the number of iterations, state-action space size, the discount factor, and the quality of exploration. In addition, we derive a functional central limit theorem, showing that the partial-sum process converges weakly to a Brownian motion. |
| title | Central Limit Theorems for Asynchronous Averaged Q-Learning |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2509.18964 |