Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909030530678784 |
|---|---|
| author | Anand, Emile Karmarkar, Ishani |
| author_facet | Anand, Emile Karmarkar, Ishani |
| contents | Many large-scale platforms and networked control systems have a centralized decision maker interacting with a massive population of agents under strict observability constraints. Motivated by such applications, we study a cooperative Markov game with a global agent and $n$ homogeneous local agents in a communication-constrained regime, where the global agent only observes a subset of $k$ local agent states per time step. We propose an alternating learning framework $(\texttt{ALTERNATING-MARL})$, where the global agent performs subsampled mean-field $Q$-learning against a fixed local policy, and local agents update by optimizing in an induced MDP. We prove that these approximate best-response dynamics converge to an $\widetilde{O}(1/\sqrt{k})$-approximate Nash Equilibrium, while separating the sample complexities between the joint state and action spaces. Finally, we validate our results in numerical simulations for multi-robot control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03759 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling Anand, Emile Karmarkar, Ishani Multiagent Systems Artificial Intelligence Machine Learning Systems and Control Optimization and Control I.2.11; I.2.1; I.2.6 Many large-scale platforms and networked control systems have a centralized decision maker interacting with a massive population of agents under strict observability constraints. Motivated by such applications, we study a cooperative Markov game with a global agent and $n$ homogeneous local agents in a communication-constrained regime, where the global agent only observes a subset of $k$ local agent states per time step. We propose an alternating learning framework $(\texttt{ALTERNATING-MARL})$, where the global agent performs subsampled mean-field $Q$-learning against a fixed local policy, and local agents update by optimizing in an induced MDP. We prove that these approximate best-response dynamics converge to an $\widetilde{O}(1/\sqrt{k})$-approximate Nash Equilibrium, while separating the sample complexities between the joint state and action spaces. Finally, we validate our results in numerical simulations for multi-robot control. |
| title | Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling |
| topic | Multiagent Systems Artificial Intelligence Machine Learning Systems and Control Optimization and Control I.2.11; I.2.1; I.2.6 |
| url | https://arxiv.org/abs/2603.03759 |