sub-optimality gap

Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis UAI 2025 Contextual Linear Bandits with Delay as Payoff ICML 2025 Experimental Design for Semiparametric Bandits COLT 2025 Gap-Dependent Bounds for Federated Q-Learning ICML 2025 Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition ICLR 2025 Model predictive control is almost optimal for restless bandits COLT 2025 Offline Learning for Combinatorial Multi-armed Bandits ICML 2025 On Constant Regret for Low-Rank MDPs UAI 2025 Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization ICML 2025 On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits ICML 2023 Optimistic PAC Reinforcement Learning: the Instance-Dependent View ALT 2023 Beyond No Regret: Instance-Dependent PAC Reinforcement Learning COLT 2022 An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality Gap NeurIPS 2021 Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap COLT 2021 Logarithmic Regret for Reinforcement Learning with Linear Function Approximation ICML 2021 Q-learning with Logarithmic Regret AISTATS 2021 ROI Maximization in Stochastic Online Decision-Making NeurIPS 2021 Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting NeurIPS 2021 Certainty Equivalence is Efficient for Linear Quadratic Control NeurIPS 2019