Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910860241272832 |
|---|---|
| author | Angiuli, Andrea Fouque, Jean-Pierre Hu, Ruimeng Raydan, Alan |
| author_facet | Angiuli, Andrea Fouque, Jean-Pierre Hu, Ruimeng Raydan, Alan |
| contents | We present the development and analysis of a reinforcement learning (RL) algorithm designed to solve continuous-space mean field game (MFG) and mean field control (MFC) problems in a unified manner. The proposed approach pairs the actor-critic (AC) paradigm with a representation of the mean field distribution via a parameterized score function, which can be efficiently updated in an online fashion, and uses Langevin dynamics to obtain samples from the resulting distribution. The AC agent and the score function are updated iteratively to converge, either to the MFG equilibrium or the MFC optimum for a given mean field problem, depending on the choice of learning rates. A straightforward modification of the algorithm allows us to solve mixed mean field control games (MFCGs). The performance of our algorithm is evaluated using linear-quadratic benchmarks in the asymptotic infinite horizon framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_10953 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces Angiuli, Andrea Fouque, Jean-Pierre Hu, Ruimeng Raydan, Alan Optimization and Control Machine Learning We present the development and analysis of a reinforcement learning (RL) algorithm designed to solve continuous-space mean field game (MFG) and mean field control (MFC) problems in a unified manner. The proposed approach pairs the actor-critic (AC) paradigm with a representation of the mean field distribution via a parameterized score function, which can be efficiently updated in an online fashion, and uses Langevin dynamics to obtain samples from the resulting distribution. The AC agent and the score function are updated iteratively to converge, either to the MFG equilibrium or the MFC optimum for a given mean field problem, depending on the choice of learning rates. A straightforward modification of the algorithm allows us to solve mixed mean field control games (MFCGs). The performance of our algorithm is evaluated using linear-quadratic benchmarks in the asymptotic infinite horizon framework. |
| title | Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces |
| topic | Optimization and Control Machine Learning |
| url | https://arxiv.org/abs/2309.10953 |