Minimax Last-Iterate Convergence in Matrix Games with Observed Actions

cs.LG, cs.GT

Submitted: 2026-09-28

Updated: 2026-09-28

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

Sources

• Decentralized Best-Response-Based Learning in Two-Player Zero-Sum Stochastic Games: A Finite-Sample Analysis
• Finite-Sample Guarantees for Learning Dynamics in Zero-Sum Polymatrix Games
• The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback
• 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
• Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback
• Nash Learning from Human Feedback
• Linear Last-iterate Convergence in Constrained Saddle-point Optimization
• Beyond Pessimism: Offline Learning in KL-regularized Games

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