← Back to all news
arXiv AI By Matthew Zurek, Yudong Chen, Josiah P. Hanna

Game-Theoretic Foundations for Undiscounted Bisimulation Metrics

Read the original on arXiv AI →

The paper establishes a game-theoretic framework for bisimulation metrics in undiscounted reinforcement learning settings, including total- and average-reward problems. By interpreting metric operators as Bellman–Shapley operators of zero-sum turn-based games, it defines unique metrics even when the discount factor equals one. The authors also explore how metric finiteness relates to MDP structure, introduce a flexible action-space modification framework, and provide bounds linking these metrics to optimal value differences and aggregation-based planning guarantees.

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 AI.

Related stories

arXiv Machine Learning
5d ago

When Is a Game a Markov Decision Process? Correspondences Between Game Theory and Reinforcement Learning

The paper establishes formal theorems linking game theory and reinforcement learning, showing that a game can be viewed as a Markov decision process in three distinct ways—definitional identity, exact reduction, or structural analogy. It systematically maps every standard game class and solution concept to corresponding reinforcement learning models, training procedures, and complexity results. The work also identifies where these correspondences break down, such as non‑stationarity, impossibility of uncoupled convergence to Nash equilibrium, and gaps between coarse correlated and correlated equilibria.

By Eduardo C. Garrido-Merch\'an
agentsreinforcement-learning
More like this →
arXiv Machine Learning
Jun 16

Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process

arXiv:2606. 16729v1 Announce Type: new Abstract: While there is an extensive body of work characterizing the sample complexity of discounted cumulative-reward MDPs, finite sample analyses for average-reward MDPs have been limited, and most existing works rely on restrictive assumptions such as ergodicity or access to a generative model.

By Jongmin Lee, Ernest K. Ryu, Vaneet Aggarwal
reinforcement-learning
More like this →