Fitted Q-Iteration via Max-Plus-Linear Approximation
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_ | 1866916646641205248 |
|---|---|
| author | Liu, Y. Kolarijani, M. A. S. |
| author_facet | Liu, Y. Kolarijani, M. A. S. |
| contents | In this study, we consider the application of max-plus-linear approximators for Q-function in offline reinforcement learning of discounted Markov decision processes. In particular, we incorporate these approximators to propose novel fitted Q-iteration (FQI) algorithms with provable convergence. Exploiting the compatibility of the Bellman operator with max-plus operations, we show that the max-plus-linear regression within each iteration of the proposed FQI algorithm reduces to simple max-plus matrix-vector multiplications. We also consider the variational implementation of the proposed algorithm which leads to a per-iteration complexity that is independent of the number of samples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08422 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fitted Q-Iteration via Max-Plus-Linear Approximation Liu, Y. Kolarijani, M. A. S. Optimization and Control Artificial Intelligence Machine Learning Systems and Control In this study, we consider the application of max-plus-linear approximators for Q-function in offline reinforcement learning of discounted Markov decision processes. In particular, we incorporate these approximators to propose novel fitted Q-iteration (FQI) algorithms with provable convergence. Exploiting the compatibility of the Bellman operator with max-plus operations, we show that the max-plus-linear regression within each iteration of the proposed FQI algorithm reduces to simple max-plus matrix-vector multiplications. We also consider the variational implementation of the proposed algorithm which leads to a per-iteration complexity that is independent of the number of samples. |
| title | Fitted Q-Iteration via Max-Plus-Linear Approximation |
| topic | Optimization and Control Artificial Intelligence Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2409.08422 |