Showing 1–20 of 34 results
/ Date/ Name
Jul 2, 2021Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement LearningOct 29, 2015Sample Complexity of Episodic Fixed-Horizon Reinforcement LearningJun 6, 2021Neural Active Learning with Performance GuaranteesMar 1, 2018On Oracle-Efficient PAC RL with Rich ObservationsDec 24, 2020Regret Bound Balancing and Elimination for Model Selection in Bandits and RLMar 22, 2017Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement LearningNov 21, 2016Memory Lens: How Much Memory Does an Agent Use?Jun 19, 2022Guarantees for Epsilon-Greedy Reinforcement Learning with Function ApproximationNov 7, 2018Policy Certificates: Towards Accountable Reinforcement LearningMay 7, 2020Reinforcement Learning with Feedback GraphsJun 22, 2021Agnostic Reinforcement Learning with Low-Rank MDPs and Rich ObservationsOct 26, 2015The Human KernelFeb 21, 2022Same Cause; Different Effects in the BrainFeb 8, 2025Design Considerations in Offline Preference-based RLMar 10, 2025Mitigating Preference Hacking in Policy Optimization with PessimismNov 18, 2024Preserving Expert-Level Privacy in Offline Reinforcement LearningJun 29, 2022Best of Both Worlds Model SelectionAug 23, 2022A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement LearningJul 22, 2015Bayesian Time-of-Flight for Realtime Shape, Illumination and AlbedoNov 5, 2015Thoughts on Massively Scalable Gaussian Processes