Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2411.07591 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917834820419584 |
|---|---|
| author | Lu, Chenbei Shi, Laixi Chen, Zaiwei Wu, Chenye Wierman, Adam |
| author_facet | Lu, Chenbei Shi, Laixi Chen, Zaiwei Wu, Chenye Wierman, Adam |
| contents | Reinforcement Learning (RL) algorithms are known to suffer from the curse of dimensionality, which refers to the fact that large-scale problems often lead to exponentially high sample complexity. A common solution is to use deep neural networks for function approximation; however, such approaches typically lack theoretical guarantees. To provably address the curse of dimensionality, we observe that many real-world problems exhibit task-specific model structures that, when properly leveraged, can improve the sample efficiency of RL. Building on this insight, we propose overcoming the curse of dimensionality by approximately factorizing the original Markov decision processes (MDPs) into smaller, independently evolving MDPs. This factorization enables the development of sample-efficient RL algorithms in both model-based and model-free settings, with the latter involving a variant of variance-reduced Q-learning. We provide improved sample complexity guarantees for both proposed algorithms. Notably, by leveraging model structure through the approximate factorization of the MDP, the dependence of sample complexity on the size of the state-action space can be exponentially reduced. Numerically, we demonstrate the practicality of our proposed methods through experiments on both synthetic MDP tasks and a wind farm-equipped storage control problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_07591 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization Lu, Chenbei Shi, Laixi Chen, Zaiwei Wu, Chenye Wierman, Adam Machine Learning Reinforcement Learning (RL) algorithms are known to suffer from the curse of dimensionality, which refers to the fact that large-scale problems often lead to exponentially high sample complexity. A common solution is to use deep neural networks for function approximation; however, such approaches typically lack theoretical guarantees. To provably address the curse of dimensionality, we observe that many real-world problems exhibit task-specific model structures that, when properly leveraged, can improve the sample efficiency of RL. Building on this insight, we propose overcoming the curse of dimensionality by approximately factorizing the original Markov decision processes (MDPs) into smaller, independently evolving MDPs. This factorization enables the development of sample-efficient RL algorithms in both model-based and model-free settings, with the latter involving a variant of variance-reduced Q-learning. We provide improved sample complexity guarantees for both proposed algorithms. Notably, by leveraging model structure through the approximate factorization of the MDP, the dependence of sample complexity on the size of the state-action space can be exponentially reduced. Numerically, we demonstrate the practicality of our proposed methods through experiments on both synthetic MDP tasks and a wind farm-equipped storage control problem. |
| title | Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2411.07591 |