Sharp Sample Complexity of KL-Regularized Reinforcement Learning
cs.LG, cs.AI
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal
- Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization
- Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret
- Taming the Noise in Reinforcement Learning via Soft Updates
- A Theory of Regularized Markov Decision Processes
- Reinforcement Learning with Deep Energy-Based Policies
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- Fast Rates for Offline Q-Learning with KL Regularization
- Fast Rates for the Regret of Offline Reinforcement Learning
- On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
- Value Mirror Descent for Reinforcement Learning
- Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis
- Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning
- RL with KL penalties is better viewed as Bayesian inference
- KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal
- Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes
- Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
- Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis
- Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model
- A Statistical Analysis of Polyak-Ruppert Averaged Q-learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis