{"total":16,"rows":[{"id":"2410.05362","title":"LLMs Are In-Context Bandit Reinforcement Learners","created":"2024-10-07","cited_by_count":29,"area":null},{"id":"2506.16658","title":"Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards","created":"2025-06-20","cited_by_count":14,"area":null},{"id":"2210.00025","title":"Artificial Replay: A Meta-Algorithm for Harnessing Historical Data in Bandits","created":"2022-09-30","cited_by_count":13,"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":"2406.19317","title":"Jump Starting Bandits with LLM-Generated Prior Knowledge","created":"2024-06-27","cited_by_count":12,"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":"2507.02762","title":"Contextual Online Pricing with (Biased) Offline Data","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2206.08556","title":"Thompson Sampling for Robust Transfer in Multi-Task Bandits","created":"2022-06-17","cited_by_count":3,"area":null},{"id":"2505.13768","title":"Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2107.03263","title":"Bandits with Stochastic Experts: Constant Regret, Empirical Experts and Episodes","created":"2021-07-07","cited_by_count":0,"area":null},{"id":"2302.03784","title":"Leveraging User-Triggered Supervision in Contextual Bandits","created":"2023-02-07","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":"2411.00287","title":"MBExplainer: Multilevel bandit-based explanations for downstream models with augmented graph embeddings","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2505.17283","title":"Deconfounded Warm-Start Thompson Sampling with Applications to Precision Medicine","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2604.02527","title":"Jump Start or False Start? A Theoretical and Empirical Evaluation of LLM-initialized Bandits","created":"2026-04-02","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}],"next_cursor":null}