Policy Optimization Achieves Data-Dependent Regret Bounds in MDPs with Unknown Transitions

arXiv:2606.31769 · cs.LG, stat.ML · Submitted 2026-06-30 · Read on arXiv

Mingyi Li, Taira Tsuchiya, Kenji Yamanishi

cs.LG, stat.ML

Submitted: 2026-06-30

Comments: 70 pages, 2 tables

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

Terminology

• Regret — 76× in this paper · explained in 3 episodes
• Loss Function — 13× in this paper · explained in 2 episodes
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Adaptivity — 4× in this paper · explained in 1 episode
• Action Space — 2× in this paper · explained in 1 episode
• Adaptive Algorithm — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• EMMA — 1× in this paper · explained in 2 episodes
• Gap-Dependent Regret — 1× in this paper · explained in 2 episodes
• Markov Decision Process (MDP) — 1× in this paper · explained in 11 episodes
• Minimax Regret — 1× in this paper · explained in 2 episodes
• Online Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Q-learning — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• Proximal Policy Optimization Algorithms

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