Tight Sample Complexity Bounds for Entropic Best Policy Identification

arXiv:2605.13717 · cs.LG, stat.ML · Submitted 2026-05-13 · Read on arXiv

cs.LG, stat.ML

Submitted: 2026-05-13

Updated: 2026-09-21

Journal ref: Proceedings of the 39th Conference on Learning Theory (COLT 2026), Proceedings of Machine Learning Research 336:2339-2398, 2026

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

Terminology

• Sample Complexity — 40× in this paper · explained in 15 episodes
• Best Policy Identification — 37× in this paper
• Regret — 30× in this paper · explained in 3 episodes
• Reinforcement Learning — 24× in this paper · explained in 4 episodes
• Generative Model — 10× in this paper · explained in 2 episodes
• Risk-sensitive Reinforcement Learning — 6× in this paper
• Action Space — 1× in this paper · explained in 1 episode
• Active Learning — 1× in this paper · explained in 6 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Minimax Regret — 1× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Theoretical Guarantees — 1× in this paper · explained in 2 episodes

Sources

• Efficient Risk-sensitive Planning via Entropic Risk Measures
• Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model

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