Switching the Loss Reduces the Cost in Batch (Offline) Reinforcement Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911974321815552 |
|---|---|
| author | Ayoub, Alex Wang, Kaiwen Liu, Vincent Robertson, Samuel McInerney, James Liang, Dawen Kallus, Nathan Szepesvári, Csaba |
| author_facet | Ayoub, Alex Wang, Kaiwen Liu, Vincent Robertson, Samuel McInerney, James Liang, Dawen Kallus, Nathan Szepesvári, Csaba |
| contents | We propose training fitted Q-iteration with log-loss (FQI-log) for batch reinforcement learning (RL). We show that the number of samples needed to learn a near-optimal policy with FQI-log scales with the accumulated cost of the optimal policy, which is zero in problems where acting optimally achieves the goal and incurs no cost. In doing so, we provide a general framework for proving small-cost bounds, i.e. bounds that scale with the optimal achievable cost, in batch RL. Moreover, we empirically verify that FQI-log uses fewer samples than FQI trained with squared loss on problems where the optimal policy reliably achieves the goal. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05385 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Switching the Loss Reduces the Cost in Batch (Offline) Reinforcement Learning Ayoub, Alex Wang, Kaiwen Liu, Vincent Robertson, Samuel McInerney, James Liang, Dawen Kallus, Nathan Szepesvári, Csaba Machine Learning We propose training fitted Q-iteration with log-loss (FQI-log) for batch reinforcement learning (RL). We show that the number of samples needed to learn a near-optimal policy with FQI-log scales with the accumulated cost of the optimal policy, which is zero in problems where acting optimally achieves the goal and incurs no cost. In doing so, we provide a general framework for proving small-cost bounds, i.e. bounds that scale with the optimal achievable cost, in batch RL. Moreover, we empirically verify that FQI-log uses fewer samples than FQI trained with squared loss on problems where the optimal policy reliably achieves the goal. |
| title | Switching the Loss Reduces the Cost in Batch (Offline) Reinforcement Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2403.05385 |