Worst-Case Regret Bounds for Exploration via Randomized Value Functions
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2019
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913510005407744 |
|---|---|
| author | Russo, Daniel |
| author_facet | Russo, Daniel |
| contents | This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning. These randomized value functions are generated by injecting random noise into the training data, making the approach compatible with many popular methods for estimating parameterized value functions. By providing a worst-case regret bound for tabular finite-horizon Markov decision processes, we show that planning with respect to these randomized value functions can induce provably efficient exploration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1906_02870 |
| institution | arXiv |
| publishDate | 2019 |
| record_format | arxiv |
| spellingShingle | Worst-Case Regret Bounds for Exploration via Randomized Value Functions Russo, Daniel Machine Learning Artificial Intelligence Systems and Control This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning. These randomized value functions are generated by injecting random noise into the training data, making the approach compatible with many popular methods for estimating parameterized value functions. By providing a worst-case regret bound for tabular finite-horizon Markov decision processes, we show that planning with respect to these randomized value functions can induce provably efficient exploration. |
| title | Worst-Case Regret Bounds for Exploration via Randomized Value Functions |
| topic | Machine Learning Artificial Intelligence Systems and Control |
| url | https://arxiv.org/abs/1906.02870 |