{"total":23,"rows":[{"id":"2404.06013","title":"Feel-Good Thompson Sampling for Contextual Dueling Bandits","created":"2024-04-09","cited_by_count":27,"area":null},{"id":"2209.14990","title":"Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms","created":"2022-09-29","cited_by_count":24,"area":null},{"id":"2305.18258","title":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2301.13857","title":"Learning in POMDPs is Sample-Efficient with Hindsight Observability","created":"2023-01-31","cited_by_count":18,"area":null},{"id":"2310.00806","title":"Bayesian Design Principles for Frequentist Sequential Learning","created":"2023-10-01","cited_by_count":18,"area":null},{"id":"2311.15238","title":"A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation","created":"2023-11-26","cited_by_count":14,"area":null},{"id":"2211.14250","title":"Model-Free Reinforcement Learning with the Decision-Estimation Coefficient","created":"2022-11-25","cited_by_count":11,"area":null},{"id":"2402.15411","title":"Optimistic Information Directed Sampling","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2510.00841","title":"LLM Routing with Dueling Feedback","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2306.14468","title":"A General Framework for Sequential Decision-Making under Adaptivity Constraints","created":"2023-06-26","cited_by_count":6,"area":null},{"id":"2307.00405","title":"Provably Efficient UCB-type Algorithms For Learning Predictive State Representations","created":"2023-07-01","cited_by_count":6,"area":null},{"id":"2307.02884","title":"Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight","created":"2023-07-06","cited_by_count":4,"area":null},{"id":"2310.11531","title":"Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach","created":"2023-10-17","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":"2406.07920","title":"Near-Optimal Learning and Planning in Separated Latent MDPs","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2403.10379","title":"Regret Minimization via Saddle Point Optimization","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2511.02123","title":"Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits","created":"2025-11-03","cited_by_count":2,"area":null},{"id":"2602.06014","title":"Optimism Stabilizes Thompson Sampling for Adaptive Inference","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2310.06243","title":"Sample-Efficient Multi-Agent RL: An Optimization Perspective","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2402.09456","title":"Optimistic Thompson Sampling for No-Regret Learning in Unknown Games","created":"2024-02-07","cited_by_count":1,"area":null},{"id":"2602.07767","title":"BFTS: Thompson Sampling with Bayesian Additive Regression Trees","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2310.13550","title":"Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes","created":"2023-10-20","cited_by_count":0,"area":null},{"id":"2610.19513","title":"High-Probability Regret Bounds for Feel-Good Thompson Sampling","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}