Statistical Foundations of Reinforcement Learning: A Non-Asymptotic Perspective
stat.ML, cs.IT, cs.LG, math.IT, math.OC
Submitted: 2026-10-30
Updated: 2026-10-30
Terminology
Sources
- On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift
- Deep Transfer $Q$-Learning for Offline Non-Stationary Reinforcement Learning
- Transfer Q-learning
- Non-Asymptotic Convergence of Stochastic Iterative Algorithms: A Lyapunov Framework
- A Non-Asymptotic Theory of Seminorm Lyapunov Stability: From Deterministic to Stochastic Iterative Algorithms
- Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning
- UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning
- Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
- Exploration-Exploitation in Constrained MDPs
- Information-theoretic Limits of Learning and Estimation
- Statistical Inference under Adaptive Sampling with LinUCB
- The Statistical Complexity of Interactive Decision Making
- Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration
- Foundations of Reinforcement Learning and Interactive Decision Making
- Statistical Inference for Misspecified Contextual Bandits
- Stable Thompson Sampling: Valid Inference via Variance Inflation
- UCB algorithms for multi-armed bandits: Precise regret and adaptive inference
- Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence
- Research Program: Theory of Learning in Dynamical Systems
- OpenAI o1 System Card
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference