No article text was recorded for this version.
regret bound gap (state-space regret scaling)
Version 1 of 145 papers49 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RL
- Blog: Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs
- Blog: Optimism in Face of a Context: Regret Guarantees for Stochastic Contextual MDP
- Blog: Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs
- Blog: Information-Theoretic Confidence Bounds for Reinforcement Learning
- Blog: Optimistic posterior sampling for reinforcement learning: worst-case regret bounds
- Blog: No-regret Exploration in Contextual Reinforcement Learning
- Blog: Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √T Regret
- Blog: Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function
- Blog: Logarithmic Regret for Linear Markov Decision Processes with Adversarial Corruptions
- Blog: Minimax-optimal reward-agnostic exploration in reinforcement learning
- Blog: Cooperative Online Learning in Stochastic and Adversarial MDPs
- Blog: Improved Corruption Robust Algorithms for Episodic Reinforcement Learning
- Blog: Nearly Optimal Policy Optimization with Stable at Any Time Guarantee
- Blog: RL with KL penalties is better viewed as Bayesian inference
- Blog: Minimax Regret Bounds for Reinforcement Learning
- Blog: Near-Optimal Sample Complexities of Divergence-based S-rectangular Distributionally Robust Reinforcement Learning
- Blog: Regret Analysis in Deterministic Reinforcement Learning
- Blog: Online Reinforcement Learning in Markov Decision Process Using Linear Programming
- Blog: Kernel-Based Reinforcement Learning: A Finite-Time Analysis
- Blog: A Reduction-based Framework for Sequential Decision Making with Delayed Feedback
- Blog: Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost
- Blog: Finding the Stochastic Shortest Path with Low Regret: the Adversarial Cost and Unknown Transition Case
- Blog: Polynomial Time Reinforcement Learning in Factored State MDPs with Linear Value Functions
- Blog: Learning Adversarial Linear Mixture Markov Decision Processes with Bandit Feedback and Unknown Transition
- Blog: Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation
- Blog: Scale-free Adversarial Reinforcement Learning
- Blog: Provably Efficient Algorithms for Multi-Objective Competitive RL
- Blog: Online Bellman Residual Algorithms with Predictive Error Guarantees
- Blog: Online Convex Optimization in Adversarial Markov Decision Processes
- Blog: Regret Bounds for Risk-Sensitive Reinforcement Learning
- Blog: Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
- Blog: A Unifying View of Optimism in Episodic Reinforcement Learning
- Blog: Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback
- Blog: Exact Unlearning in Reinforcement Learning
- Blog: Provably Efficient Reinforcement Learning via Surprise Bound
- Blog: Private Reinforcement Learning with PAC and Regret Guarantees
- Blog: Learning in online MDPs: is there a price for handling the communicating case?
- Blog: Why is Posterior Sampling Better than Optimism for Reinforcement Learning?
- Blog: Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities
- Blog: Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration
- Blog: Regime Switching Bandits
- Blog: IMED-RL: Regret optimal learning of ergodic Markov decision processes
- Blog: Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs
- Blog: Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes
History & citation
Current · Permanent link
- This direction split from Closing Regret Gaps in Reinforcement Learning Theory (76% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_regret_bound_gap_state_space_regret_scal_d00e0274,
title = {regret bound gap (state-space regret scaling)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/regret-bound-gap-state-space-regret-scaling/rdr_d00e02746bd4489faf4a72ed335dd9ec},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_regret_bound_gap_state_space_regret_scal_d00e0274_v1,
title = {regret bound gap (state-space regret scaling)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/regret-bound-gap-state-space-regret-scaling/rdr_d00e02746bd4489faf4a72ed335dd9ec/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}