Research
Decentralized Bandit Learning of Markov Perfect Equilibria
arXiv:2610.14333v1 Announce Type: new Abstract: We study decentralized bandit learning in discounted infinite-horizon, general-sum Markov games with continuous actions. Agents observe the public state
arXiv:2610.14333v1 Announce Type: new 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.
Related
- High-Probability Nash Regret for Decentralized Learning in Markov alpha-Potential Games: Episodic and Fully Online Asynchronous Algorithms with Applications to Markov Congestion Games
- Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions
- Equilibrium Learning in Unbounded Stochastic Games with Gaussian Transitions
Source: arXiv cs.LG | 2026-10-14