← Back to all news
arXiv Machine Learning By Philip Jordan, Maryam Kamgarpour

Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics

Read the original on arXiv Machine Learning →

The paper investigates learning Nash equilibria in partially observable Markov games (POMGs) where agents cannot fully observe the state. By focusing on a subclass with independent state transitions and a Markov potential game structure, the authors propose an independent learning algorithm that allows agents to converge to an approximate Nash equilibrium using only their own observations and actions, without communication. Under a filter stability assumption, finite‑history policies are shown to approximate the POMG sufficiently, enabling a surrogate near‑potential Markov game and yielding quasi‑polynomial sample and computational complexity.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 31

Aspiration-based Perturbed Learning Automata in Games with Noisy Utility Measurements. Part A: Stochastic Stability in Non-zero-Sum Games

The paper introduces aspiration-based perturbed learning automata (APLA), a payoff‑based learning scheme that incorporates an aspiration factor to reinforce action selection in distributed multi‑player games. It presents a stochastic stability analysis of APLA in positive‑utility games with noisy observations, establishing that the infinite‑dimensional Markov chain induced by the dynamics can be reduced to a finite‑dimensional one. This work extends previous results beyond potential and coordination games to generic non‑zero‑sum games, with a second part focusing on weakly acyclic games.

By Georgios C. Chasparis
More like this →
arXiv Machine Learning
Sep 2

NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games

NashDreamer is a new model-based reinforcement learning framework designed for two-player zero-sum imperfect-information games. It introduces a centralized Multi-Agent Recurrent State-Space Model that separates environment dynamics from player strategy effects, enabling the use of any policy gradient algorithm while preserving convergence guarantees to Nash equilibria. Experiments on four benchmark games show that NashDreamer achieves significantly better sample efficiency than model-free baselines early in training, and the authors analyze its optimization landscape, noting a potential vulnerability to posterior collapse in stochastic settings.

By Tom\'a\v{s} Hole\v{c}ek, Viliam Lis\'y
agentsreinforcement-learningbenchmarks
More like this →