{"total":38,"rows":[{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2403.15371","title":"Can large language models explore in-context?","created":"2024-03-22","cited_by_count":76,"area":null},{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2108.06422","title":"Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models","created":"2021-08-13","cited_by_count":24,"area":null},{"id":"2202.10066","title":"Multi-task Representation Learning with Stochastic Linear Bandits","created":"2022-02-21","cited_by_count":21,"area":null},{"id":"2307.09943","title":"Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay","created":"2023-07-19","cited_by_count":17,"area":null},{"id":"2107.05320","title":"Metalearning Linear Bandits by Prior Update","created":"2021-07-12","cited_by_count":16,"area":null},{"id":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2507.14057","title":"Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design","created":"2025-07-18","cited_by_count":12,"area":null},{"id":"2202.12888","title":"Meta-Learning for Simple Regret Minimization","created":"2022-02-25","cited_by_count":10,"area":null},{"id":"2311.12244","title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2212.04720","title":"Multi-Task Off-Policy Learning from Bandit Feedback","created":"2022-12-09","cited_by_count":9,"area":null},{"id":"2307.02295","title":"Meta-Learning Adversarial Bandit Algorithms","created":"2023-07-05","cited_by_count":8,"area":null},{"id":"2408.05586","title":"Meta Clustering of Neural Bandits","created":"2024-08-10","cited_by_count":7,"area":null},{"id":"2206.10716","title":"Meta Reinforcement Learning with Finite Training Tasks -- a Density Estimation Approach","created":"2022-06-21","cited_by_count":6,"area":null},{"id":"2310.14968","title":"Bayesian Active Learning in the Presence of Nuisance Parameters","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2402.17739","title":"reBandit: Random Effects based Online RL algorithm for Reducing Cannabis Use","created":"2024-02-27","cited_by_count":6,"area":null},{"id":"2502.07064","title":"Contextual Thompson Sampling via Generation of Missing Data","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2201.01902","title":"Gaussian Imagination in Bandit Learning","created":"2022-01-06","cited_by_count":5,"area":null},{"id":"2202.00602","title":"Meta-Learning Hypothesis Spaces for Sequential Decision-making","created":"2022-02-01","cited_by_count":5,"area":null},{"id":"2205.14128","title":"Meta-Learning Adversarial Bandits","created":"2022-05-27","cited_by_count":5,"area":null},{"id":"2310.07518","title":"Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2505.23165","title":"Best Arm Identification with Possibly Biased Offline Data","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2111.04835","title":"Safe Data Collection for Offline and Online Policy Learning","created":"2021-11-08","cited_by_count":4,"area":null},{"id":"2210.15513","title":"Lifelong Bandit Optimization: No Prior and No Regret","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2402.05878","title":"Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2507.02762","title":"Contextual Online Pricing with (Biased) Offline Data","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2210.03528","title":"Tractable Optimality in Episodic Latent MABs","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2404.12219","title":"A Quadrature Approach for General-Purpose Batch Bayesian Optimization via Probabilistic Lifting","created":"2024-04-18","cited_by_count":3,"area":null},{"id":"2412.20824","title":"Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2504.04505","title":"A Classification View on Meta Learning Bandits","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2207.06917","title":"Online Bayesian Meta-Learning for Cognitive Tracking Radar","created":"2022-07-07","cited_by_count":0,"area":null},{"id":"2305.11908","title":"Sequential Best-Arm Identification with Application to Brain-Computer Interface","created":"2023-05-17","cited_by_count":0,"area":null},{"id":"2306.09136","title":"Finite-Time Logarithmic Bayes Regret Upper Bounds","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2309.01453","title":"Interactive Graph Convolutional Filtering","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2605.10289","title":"Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2610.17203","title":"Online LLM Personalization from Pairwise Preferences Across Users","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}