{"total":24,"rows":[{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32,"area":null},{"id":"2206.07659","title":"Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2206.13497","title":"Robustness Implies Generalization via Data-Dependent Generalization Bounds","created":"2022-06-27","cited_by_count":23,"area":null},{"id":"2107.03635","title":"Sublinear Regret for Learning POMDPs","created":"2021-07-08","cited_by_count":19,"area":null},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15,"area":null},{"id":"2210.00701","title":"Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2212.13540","title":"Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2022-12-27","cited_by_count":13,"area":null},{"id":"2209.14414","title":"Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2202.03463","title":"On learning Whittle index policy for restless bandits with scalable regret","created":"2022-02-07","cited_by_count":10,"area":null},{"id":"2203.08248","title":"Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling","created":"2022-03-15","cited_by_count":10,"area":null},{"id":"2112.14195","title":"Exponential Family Model-Based Reinforcement Learning via Score Matching","created":"2021-12-28","cited_by_count":5,"area":null},{"id":"2302.11634","title":"Provably Efficient Reinforcement Learning via Surprise Bound","created":"2023-02-22","cited_by_count":4,"area":null},{"id":"2210.13075","title":"Hardness in Markov Decision Processes: Theory and Practice","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2310.19861","title":"Posterior Sampling for Competitive RL: Function Approximation and Partial Observation","created":"2023-10-30","cited_by_count":3,"area":null},{"id":"2305.02093","title":"Efficient Online Decision Tree Learning with Active Feature Acquisition","created":"2023-05-03","cited_by_count":2,"area":null},{"id":"2106.08771","title":"Reinforcement Learning for Markovian Bandits: Is Posterior Sampling more Scalable than Optimism?","created":"2021-06-16","cited_by_count":1,"area":null},{"id":"2202.13863","title":"Provably Efficient Convergence of Primal-Dual Actor-Critic with Nonlinear Function Approximation","created":"2022-02-28","cited_by_count":1,"area":null},{"id":"2202.05799","title":"Rate-matching the regret lower-bound in the linear quadratic regulator with unknown dynamics","created":"2022-02-11","cited_by_count":0,"area":null},{"id":"2412.14075","title":"Online MDP with Transition Prototypes: A Robust Adaptive Approach","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2601.14710","title":"Case-Guided Sequential Assay Planning in Drug Discovery","created":"2026-01-21","cited_by_count":0,"area":null}],"next_cursor":null}