Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence
Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du
cs.LG, stat.ML
Submitted: 2026-07-22
Comments: 78 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Provably Efficient Exploration in Policy Optimization
- Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP
- A Unifying View of Optimism in Episodic Reinforcement Learning
- Towards Tractable Optimism in Model-Based Reinforcement Learning
- Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs
- Near-Optimal Randomized Exploration for Tabular Markov Decision Processes
- $Q$-learning with Logarithmic Regret
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks