Closing the Horizon Gap in Policy Optimization for Adversarial MDPs

arXiv:2610.12362 · cs.LG, stat.ML · Submitted 2026-10-08 · Read on arXiv

cs.LG, stat.ML

Submitted: 2026-10-08

Updated: 2026-10-08

Terminology

• Regret — 52× in this paper · explained in 3 episodes
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• Loss Function — 2× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Markov Decision Process (MDP) — 1× in this paper · explained in 11 episodes
• Q-learning — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• Policy Optimization Achieves Data-Dependent Regret Bounds in MDPs with Unknown Transitions
• A unified view of entropy-regularized Markov decision processes
• Proximal Policy Optimization Algorithms
• Reinforcement Learning from Adversarial Preferences in Tabular MDPs

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks