Metraipolis › archive › dc_3f3773399bf4
Bayesian Learning of Parametric Mean Field Games with Common Noise — arXiv:2610.23387
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.23387
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:44:35.135Z
- SHA-256 of the archived text
d86c74a265bc218330bfacd8093dc23e1abcc1699f41f10a45a2ecb1459f63cd- Stable URL of this page
https://metraipolis.com/documento/dc_3f3773399bf4
How to cite
Bayesian Learning of Parametric Mean Field Games with Common Noise — arXiv:2610.23387 — arXiv (en), https://arxiv.org/abs/2610.23387 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f3773399bf4 (Metraipolis archive dc_3f3773399bf4, sha256 d86c74a265bc218330bfacd8093dc23e1abcc1699f41f10a45a2ecb1459f63cd)
BibTeX
@misc{dc3f3773399bf4,
title = {Bayesian Learning of Parametric Mean Field Games with Common Noise — arXiv:2610.23387},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.23387},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f3773399bf4; sha256 d86c74a265bc218330bfacd8093dc23e1abcc1699f41f10a45a2ecb1459f63cd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23387. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study the inverse problem of recovering unknown parameters governing the dynamics and rewards of Mean Field Games (MFGs) from partial observations of population trajectories, made stochastic by common noise. The observer seeks to recover a consistent parameter $\theta$ via Bayesian inference, facing the challenge that evaluating the likelihood requires solving a new Nash equilibrium (NE) for each candidate $\theta$. Due to common noise, the mean-field evolution is stochastic and equilibrium policies are population dependent, which makes solving for each parameter computationally expensive. To overcome this, we introduce the Bayesian-Extended Mean Field Game (BE-MFG), whose single NE simultaneously encodes equilibrium policies for all parameters, enabling efficient learning of the conditional density of mean-field trajectories. We formalize parameter consistency and identifiability in MFGs with common noise and investigate conditions under which consistent parameter recovery is guaranteed. On three synthetic environments of various complexity, we recover the ground-truth parameter accurately from a small number of partial, stochastic observations, outperforming an adaptation of inverse reinforcement learning for MFGs. A fourth experiment, on public electricity market data, suggests that the approach can also be applied to real-world data. Tema degli esploratori: economia dei servizi IA (elenco arXiv cs.GT, nuovi lavori del giorno). Categorie arXiv: Computer Science and Game Theory (cs.GT). Pagina del lavoro: https://arxiv.org/abs/2610.23387 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T08:40:39.831Z dalla pagina https://arxiv.org/list/cs.GT/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).