Learning the Model While Learning Q: Finite-Time Sample Complexity of Online SyncMBQ
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_ | 1866908919598678016 |
|---|---|
| author | Lim, Han-Dong Lee, HyeAnn Lee, Donghwan |
| author_facet | Lim, Han-Dong Lee, HyeAnn Lee, Donghwan |
| contents | Reinforcement learning has witnessed significant advancements, particularly with the emergence of model-based approaches. Among these, $Q$-learning has proven to be a powerful algorithm in model-free settings. However, the extension of $Q$-learning to a model-based framework remains relatively unexplored. In this paper, we investigate the sample complexity of $Q$-learning when integrated with a model-based approach. The proposed algorihtms learns both the model and Q-value in an online manner. We demonstrate a near-optimal sample complexity result within a broad range of step sizes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11877 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning the Model While Learning Q: Finite-Time Sample Complexity of Online SyncMBQ Lim, Han-Dong Lee, HyeAnn Lee, Donghwan Machine Learning Artificial Intelligence Reinforcement learning has witnessed significant advancements, particularly with the emergence of model-based approaches. Among these, $Q$-learning has proven to be a powerful algorithm in model-free settings. However, the extension of $Q$-learning to a model-based framework remains relatively unexplored. In this paper, we investigate the sample complexity of $Q$-learning when integrated with a model-based approach. The proposed algorihtms learns both the model and Q-value in an online manner. We demonstrate a near-optimal sample complexity result within a broad range of step sizes. |
| title | Learning the Model While Learning Q: Finite-Time Sample Complexity of Online SyncMBQ |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2402.11877 |