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

We study the problem of learning Nash equilibria in offline two-player zero-sum Markov games. While existing approaches often rely on explicit pessimism to address distribution shift, we show that KL regularization alone suffices to stabilize learning and guarantee convergence. We first introduce Regularized Offline Sequential Equilibrium (ROSE), a theoretical framework that achieves a fast $\widetilde{\mathcal{O}}(1/n)$ convergence rate under \textit{unilateral concentrability}, improving over the standard $\widetilde{\mathcal{O}}(1/\sqrt{n})$ rates in unregularized settings. We then propose Sequential Offline Self-play Mirror Descent (SOS-MD), a practical model-free algorithm based on least-squares value estimation and iterative self-play updates. We prove that the last iterate of SOS-MD attains the same $\widetilde{\mathcal{O}}(1/n)$ statistical rate up to a vanishing optimization error of order $\widetilde{\mathcal{O}}(1/\sqrt{T})$ in the number of self-play iterations $T$.

In multi-agent reinforcement learning (MARL), inter-agent communication is effective for improving performance under partial observability. Representation learning-based approaches enable decentralized agents to learn messages grounded in their own observations, but they rely only on current observations and cannot convey information accumulated over time. We propose Dreamer-CPC, a decentralized model-based MARL method that integrates message learning based on Collective Predictive Coding (CPC) into the world model of DreamerV3. Each agent independently maintains a world model and a message module, and infers and exchanges messages from the latent states of the world model that reflect the history of past observations and actions. We evaluated Dreamer-CPC in two environments: Observer, a non-cooperative information-sharing task, and CatchApple, a newly introduced task in which task-relevant observations are temporarily missing. In both environments, Dreamer-CPC outperformed IPPO-CPC, an existing CPC-based method that generates messages from current observations, as well as no-communication baselines. In particular, in CatchApple, Dreamer-CPC achieved 4 to 5 times the episode return of IPPO-CPC, demonstrating effective coordination where other methods fail due to missing observations. These results suggest that communication grounded in the latent dynamics of world models can support decentralized decision-making when current observations alone are insufficient.

We present a finite-sample analysis of decentralized learning in two-player zero-sum matrix games and stochastic games, with a focus on best-response-based learning algorithms. In matrix games, the learning algorithm is payoff-based and symmetric: each player updates its policy using only its own payoff observations, incrementally moving toward an estimated smoothed best response to the opponent's latest policy. For stochastic games, we build on this matrix-game primitive to develop a learning algorithm called value iteration with smoothed best response (VI-SBR), which combines smoothed-best-response learning in induced matrix games with a decentralized, model-free approximation of minimax value iteration. We establish finite-sample guarantees in both settings. For matrix games, our results imply a sample complexity of $\mathcal{O}(ε^{-1})$ for finding an $ε$-Nash distribution and, with explicit exploration, $\tilde{\mathcal{O}}(ε^{-8})$ for finding an $ε$-Nash equilibrium. For stochastic games, we prove that the exploration-enhanced VI-SBR algorithm achieves a sample complexity of $\tilde{\mathcal{O}}(ε^{-8})$ for finding an $ε$-Nash equilibrium. Technically, our analysis develops a coupled Lyapunov-drift framework. This framework simultaneously handles stochastic iterative algorithms with multiple interacting stochastic iterates, the non-zero-sum auxiliary games generated by independently updated value functions, and the time-inhomogeneous Markovian noise induced by time-varying policies. The resulting tools may be useful more broadly for analyzing learning algorithms with coupled stochastic iterates and nonstationary sampling processes.