Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2021
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917701914460160 |
|---|---|
| author | Vijayan, Nithia A, Prashanth L. |
| author_facet | Vijayan, Nithia A, Prashanth L. |
| contents | We propose two policy gradient algorithms for solving the problem of control in an off-policy reinforcement learning (RL) context. Both algorithms incorporate a smoothed functional (SF) based gradient estimation scheme. The first algorithm is a straightforward combination of importance sampling-based off-policy evaluation with SF-based gradient estimation. The second algorithm, inspired by the stochastic variance-reduced gradient (SVRG) algorithm, incorporates variance reduction in the update iteration. For both algorithms, we derive non-asymptotic bounds that establish convergence to an approximate stationary point. From these results, we infer that the first algorithm converges at a rate that is comparable to the well-known REINFORCE algorithm in an off-policy RL context, while the second algorithm exhibits an improved rate of convergence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2101_02137 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint Vijayan, Nithia A, Prashanth L. Machine Learning We propose two policy gradient algorithms for solving the problem of control in an off-policy reinforcement learning (RL) context. Both algorithms incorporate a smoothed functional (SF) based gradient estimation scheme. The first algorithm is a straightforward combination of importance sampling-based off-policy evaluation with SF-based gradient estimation. The second algorithm, inspired by the stochastic variance-reduced gradient (SVRG) algorithm, incorporates variance reduction in the update iteration. For both algorithms, we derive non-asymptotic bounds that establish convergence to an approximate stationary point. From these results, we infer that the first algorithm converges at a rate that is comparable to the well-known REINFORCE algorithm in an off-policy RL context, while the second algorithm exhibits an improved rate of convergence. |
| title | Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2101.02137 |