Interacting Particle Systems for Fast Linear Quadratic RL
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917024866762752 |
|---|---|
| author | Joshi, Anant A Chang, Heng-Sheng Taghvaei, Amirhossein Mehta, Prashant G Meyn, Sean P. |
| author_facet | Joshi, Anant A Chang, Heng-Sheng Taghvaei, Amirhossein Mehta, Prashant G Meyn, Sean P. |
| contents | This paper is concerned with the design of algorithms based on systems of interacting particles to represent, approximate, and learn the optimal control law for reinforcement learning (RL). The primary contribution is that convergence rates are greatly accelerated by the interactions between particles. Theory focuses on the linear quadratic stochastic optimal control problem for which a complete and novel theory is presented. Apart from the new algorithm, sample complexity bounds are obtained, and it is shown that the mean square error scales as $1/N$ where $N$ is the number of particles. The theoretical results and algorithms are illustrated with numerical experiments and comparisons with other recent approaches, where the faster convergence of the proposed algorithm is numerically demonstrated. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_11057 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Interacting Particle Systems for Fast Linear Quadratic RL Joshi, Anant A Chang, Heng-Sheng Taghvaei, Amirhossein Mehta, Prashant G Meyn, Sean P. Systems and Control This paper is concerned with the design of algorithms based on systems of interacting particles to represent, approximate, and learn the optimal control law for reinforcement learning (RL). The primary contribution is that convergence rates are greatly accelerated by the interactions between particles. Theory focuses on the linear quadratic stochastic optimal control problem for which a complete and novel theory is presented. Apart from the new algorithm, sample complexity bounds are obtained, and it is shown that the mean square error scales as $1/N$ where $N$ is the number of particles. The theoretical results and algorithms are illustrated with numerical experiments and comparisons with other recent approaches, where the faster convergence of the proposed algorithm is numerically demonstrated. |
| title | Interacting Particle Systems for Fast Linear Quadratic RL |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2406.11057 |