Offline-Online Reinforcement Learning for Linear Mixture MDPs
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914470112002048 |
|---|---|
| author | Zhang, Zhongjun Sinclair, Sean R. |
| author_facet | Zhang, Zhongjun Sinclair, Sean R. |
| contents | We study offline-online reinforcement learning in linear mixture Markov decision processes (MDPs) under environment shift. In the offline phase, data are collected by an unknown behavior policy and may come from a mismatched environment, while in the online phase the learner interacts with the target environment. We propose an algorithm that adaptively leverages offline data. When the offline data are informative, either due to sufficient coverage or small environment shift, the algorithm provably improves over purely online learning. When the offline data are uninformative, it safely ignores them and matches the online-only performance. We establish regret upper bounds that explicitly characterize when offline data are beneficial, together with nearly matching lower bounds. Numerical experiments further corroborate our theoretical findings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11994 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Offline-Online Reinforcement Learning for Linear Mixture MDPs Zhang, Zhongjun Sinclair, Sean R. Machine Learning Optimization and Control We study offline-online reinforcement learning in linear mixture Markov decision processes (MDPs) under environment shift. In the offline phase, data are collected by an unknown behavior policy and may come from a mismatched environment, while in the online phase the learner interacts with the target environment. We propose an algorithm that adaptively leverages offline data. When the offline data are informative, either due to sufficient coverage or small environment shift, the algorithm provably improves over purely online learning. When the offline data are uninformative, it safely ignores them and matches the online-only performance. We establish regret upper bounds that explicitly characterize when offline data are beneficial, together with nearly matching lower bounds. Numerical experiments further corroborate our theoretical findings. |
| title | Offline-Online Reinforcement Learning for Linear Mixture MDPs |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2604.11994 |