Online Reinforcement Learning with Passive Memory
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929550292680704 |
|---|---|
| author | Pattanaik, Anay Varshney, Lav R. |
| author_facet | Pattanaik, Anay Varshney, Lav R. |
| contents | This paper considers an online reinforcement learning algorithm that leverages pre-collected data (passive memory) from the environment for online interaction. We show that using passive memory improves performance and further provide theoretical guarantees for regret that turns out to be near-minimax optimal. Results show that the quality of passive memory determines sub-optimality of the incurred regret. The proposed approach and results hold in both continuous and discrete state-action spaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_14665 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Online Reinforcement Learning with Passive Memory Pattanaik, Anay Varshney, Lav R. Machine Learning Artificial Intelligence This paper considers an online reinforcement learning algorithm that leverages pre-collected data (passive memory) from the environment for online interaction. We show that using passive memory improves performance and further provide theoretical guarantees for regret that turns out to be near-minimax optimal. Results show that the quality of passive memory determines sub-optimality of the incurred regret. The proposed approach and results hold in both continuous and discrete state-action spaces. |
| title | Online Reinforcement Learning with Passive Memory |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2410.14665 |