{"total":41,"rows":[{"id":"2110.00871","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","created":"2021-10-02","cited_by_count":66,"area":null},{"id":"2102.06129","title":"Meta-Thompson Sampling","created":"2021-02-11","cited_by_count":63,"area":null},{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2107.06196","title":"No Regrets for Learning the Prior in Bandits","created":"2021-07-13","cited_by_count":30,"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":"2202.01454","title":"Deep Hierarchy in Bandits","created":"2022-02-03","cited_by_count":19,"area":null},{"id":"2106.05608","title":"Thompson Sampling with a Mixture Prior","created":"2021-06-10","cited_by_count":16,"area":null},{"id":"2201.11211","title":"Learning Mixtures of Linear Dynamical Systems","created":"2022-01-26","cited_by_count":15,"area":null},{"id":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2110.08627","title":"Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits","created":"2021-10-16","cited_by_count":13,"area":null},{"id":"2301.07040","title":"Optimal Algorithms for Latent Bandits with Cluster Structure","created":"2023-01-17","cited_by_count":12,"area":null},{"id":"2306.14834","title":"Scalable Neural Contextual Bandit for Recommender Systems","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2110.12175","title":"Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits","created":"2021-10-23","cited_by_count":10,"area":null},{"id":"2106.04887","title":"Interaction-Grounded Learning","created":"2021-06-09","cited_by_count":9,"area":null},{"id":"2202.13001","title":"Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms","created":"2022-02-25","cited_by_count":8,"area":null},{"id":"2107.11533","title":"Combining Online Learning and Offline Learning for Contextual Bandits with Deficient Support","created":"2021-07-24","cited_by_count":7,"area":null},{"id":"2408.05586","title":"Meta Clustering of Neural Bandits","created":"2024-08-10","cited_by_count":7,"area":null},{"id":"2109.01656","title":"Thompson Sampling for Bandits with Clustered Arms","created":"2021-09-06","cited_by_count":6,"area":null},{"id":"2106.05378","title":"Feature and Parameter Selection in Stochastic Linear Bandits","created":"2021-06-09","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":"2409.11521","title":"Partially Observable Contextual Bandits with Linear Payoffs","created":"2024-09-17","cited_by_count":5,"area":null},{"id":"2306.13053","title":"Context-lumpable stochastic bandits","created":"2023-06-22","cited_by_count":4,"area":null},{"id":"2307.13916","title":"Online learning in bandits with predicted context","created":"2023-07-26","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":"2502.20153","title":"Transfer Learning in Latent Contextual Bandits with Covariate Shift Through Causal Transportability","created":"2025-02-27","cited_by_count":4,"area":null},{"id":"2207.03635","title":"Information-Gathering in Latent Bandits","created":"2022-07-08","cited_by_count":2,"area":null},{"id":"2410.01331","title":"Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2411.11794","title":"Competing Bandits in Decentralized Contextual Matching Markets","created":"2024-11-18","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":"2506.12389","title":"Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2302.05765","title":"Adversarial Online Collaborative Filtering","created":"2023-02-11","cited_by_count":0,"area":null},{"id":"2305.01470","title":"Stochastic Contextual Bandits with Graph-based Contexts","created":"2023-05-02","cited_by_count":0,"area":null},{"id":"2305.18305","title":"High Accuracy and Low Regret for User-Cold-Start Using Latent Bandits","created":"2023-05-12","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":"2407.16239","title":"Identifiable Latent Bandits: Leveraging observational data for personalized decision-making","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2503.04518","title":"Leveraging priors on distribution functions for multi-arm bandits","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2505.18269","title":"Representative Action Selection for Large Action Space Bandit Families","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2508.05367","title":"Latent Preference Bandits","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2605.07304","title":"Latent Order Bandits","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.00846","title":"CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM","created":"2026-05-30","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}