Optimal Sample Complexity of Stable Discounted Markov Decision Processes

arXiv:2302.07477 · cs.LG, math.OC, stat.ML · Submitted 2023-02-15 · Read on arXiv

cs.LG, math.OC, stat.ML

Submitted: 2023-02-15

Updated: 2026-09-18

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

Terminology

• Sample Complexity — 67× in this paper · explained in 15 episodes
• Q-learning — 37× in this paper · explained in 3 episodes
• Reinforcement Learning — 11× in this paper · explained in 4 episodes
• Generative Model — 5× in this paper · explained in 2 episodes
• Reward Function — 5× in this paper · explained in 2 episodes
• Action Space — 3× in this paper · explained in 1 episode
• Markov Decision Process (MDP) — 3× in this paper · explained in 11 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptivity — 1× in this paper · explained in 1 episode

Sources

• Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis
• CAD2RL: Real Single-Image Flight without a Single Real Image
• Primal-Dual $\pi$ Learning: Sample Complexity and Sublinear Run Time for Ergodic Markov Decision Problems

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