Homogenization of Multi-agent Learning Dynamics in Finite-state Markov Games
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909660614754304 |
|---|---|
| author | Kerzreho, Yann |
| author_facet | Kerzreho, Yann |
| contents | This paper introduces a new approach for approximating the learning dynamics of multiple reinforcement learning (RL) agents interacting in a finite-state Markov game. The idea is to rescale the learning process by simultaneously reducing the learning rate and increasing the update frequency, effectively treating the agent's parameters as a slow-evolving variable influenced by the fast-mixing game state. Under mild assumptions-ergodicity of the state process and continuity of the updates-we prove the convergence of this rescaled process to an ordinary differential equation (ODE). This ODE provides a tractable, deterministic approximation of the agent's learning dynamics. An implementation of the framework is available at\,: https://github.com/yannKerzreho/MarkovGameApproximation |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21079 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Homogenization of Multi-agent Learning Dynamics in Finite-state Markov Games Kerzreho, Yann Machine Learning Probability This paper introduces a new approach for approximating the learning dynamics of multiple reinforcement learning (RL) agents interacting in a finite-state Markov game. The idea is to rescale the learning process by simultaneously reducing the learning rate and increasing the update frequency, effectively treating the agent's parameters as a slow-evolving variable influenced by the fast-mixing game state. Under mild assumptions-ergodicity of the state process and continuity of the updates-we prove the convergence of this rescaled process to an ordinary differential equation (ODE). This ODE provides a tractable, deterministic approximation of the agent's learning dynamics. An implementation of the framework is available at\,: https://github.com/yannKerzreho/MarkovGameApproximation |
| title | Homogenization of Multi-agent Learning Dynamics in Finite-state Markov Games |
| topic | Machine Learning Probability |
| url | https://arxiv.org/abs/2506.21079 |