← Back to all news
arXiv Machine Learning By Tom\'a\v{s} Hole\v{c}ek, Viliam Lis\'y

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

Read the original on arXiv Machine Learning →

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.

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
3d ago

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

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.

By Philip Jordan, Maryam Kamgarpour
agentsreinforcement-learning
More like this →