Fast Last-Iterate Convergence in Zero-Sum Markov Games with Bandit Feedback

cs.LG, cs.GT

Submitted: 2026-10-05

Updated: 2026-10-05

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Tight Last-Iterate Convergence of the Extragradient and the Optimistic Gradient Descent-Ascent Algorithm for Constrained Monotone Variational Inequalities
• Decentralized Best-Response-Based Learning in Two-Player Zero-Sum Stochastic Games: A Finite-Sample Analysis
• Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization
• Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier
• Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions
• Linear Last-iterate Convergence in Constrained Saddle-point Optimization
• Minimax Last-Iterate Convergence in Matrix Games with Observed Actions

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks