Markov-Nash equilibria in mean-field games under model uncertainty
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917803941953536 |
|---|---|
| author | Langner, Johannes Neufeld, Ariel Park, Kyunghyun |
| author_facet | Langner, Johannes Neufeld, Ariel Park, Kyunghyun |
| contents | We propose and analyze a framework for mean-field Markov games under model uncertainty. In this framework, a state-measure flow describing the collective behavior of a population affects the given reward function as well as the unknown transition kernel of the representative agent. The agent's objective is to choose an optimal Markov policy in order to maximize her worst-case expected reward, where worst-case refers to the most adverse scenario among all transition kernels considered to be feasible to describe the unknown true law of the environment. We prove the existence of a mean-field equilibrium under model uncertainty, where the agent chooses the optimal policy that maximizes the worst-case expected reward, and the state-measure flow aligns with the agent's state distribution under the optimal policy and the worst-case transition kernel. Moreover, we prove that for suitable multi-agent Markov games under model uncertainty the optimal policy from the mean-field equilibrium forms an approximate Markov-Nash equilibrium whenever the number of agents is large enough. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11652 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Markov-Nash equilibria in mean-field games under model uncertainty Langner, Johannes Neufeld, Ariel Park, Kyunghyun Optimization and Control Probability We propose and analyze a framework for mean-field Markov games under model uncertainty. In this framework, a state-measure flow describing the collective behavior of a population affects the given reward function as well as the unknown transition kernel of the representative agent. The agent's objective is to choose an optimal Markov policy in order to maximize her worst-case expected reward, where worst-case refers to the most adverse scenario among all transition kernels considered to be feasible to describe the unknown true law of the environment. We prove the existence of a mean-field equilibrium under model uncertainty, where the agent chooses the optimal policy that maximizes the worst-case expected reward, and the state-measure flow aligns with the agent's state distribution under the optimal policy and the worst-case transition kernel. Moreover, we prove that for suitable multi-agent Markov games under model uncertainty the optimal policy from the mean-field equilibrium forms an approximate Markov-Nash equilibrium whenever the number of agents is large enough. |
| title | Markov-Nash equilibria in mean-field games under model uncertainty |
| topic | Optimization and Control Probability |
| url | https://arxiv.org/abs/2410.11652 |