arXiv · 2610.14333
Decentralized Bandit Learning of Markov Perfect Equilibria
Abstract
We study decentralized bandit learning in discounted infinite-horizon, general-sum Markov games with continuous actions. Agents observe the public state, but only their own realized rewards, and use simultaneous perturbation stochastic approximation to update their actions. Under strong monotonicity of the negative running-reward gradients and sufficiently small time steps, we prove that the fully decentralized procedure converges almost surely to the unique stationary Markov perfect equilibrium. We obtain an $O(n^{-1/2})$ convergence rate and present a natural extension to episodic finite-horizon learning.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Felix Höfer, H. Mete Soner. 2026-10-09. Decentralized Bandit Learning of Markov Perfect Equilibria. https://searcharxiv.com/abs/2610.14333
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.