{"total":17,"rows":[{"id":"2403.07213","title":"Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits","created":"2024-03-11","cited_by_count":27,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2102.00725","title":"Generalized non-stationary bandits","created":"2021-02-01","cited_by_count":8,"area":null},{"id":"2110.11819","title":"A Last Switch Dependent Analysis of Satiation and Seasonality in Bandits","created":"2021-10-22","cited_by_count":8,"area":null},{"id":"2302.08345","title":"Linear Bandits with Memory: from Rotting to Rising","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2106.15808","title":"Optimal Epidemic Control as a Contextual Combinatorial Bandit with Budget","created":"2021-06-30","cited_by_count":5,"area":null},{"id":"2108.02307","title":"Regret Analysis of Learning-Based MPC with Partially-Unknown Cost Function","created":"2021-08-04","cited_by_count":5,"area":null},{"id":"2201.12975","title":"Rotting Infinitely Many-armed Bandits","created":"2022-01-31","cited_by_count":4,"area":null},{"id":"2204.11174","title":"Complete Policy Regret Bounds for Tallying Bandits","created":"2022-04-24","cited_by_count":3,"area":null},{"id":"2201.00486","title":"Using Non-Stationary Bandits for Learning in Repeated Cournot Games with Non-Stationary Demand","created":"2022-01-03","cited_by_count":2,"area":null},{"id":"2205.10113","title":"Evolutionary Multi-Armed Bandits with Genetic Thompson Sampling","created":"2022-04-26","cited_by_count":2,"area":null},{"id":"2305.02955","title":"Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2608.15848","title":"Generalized Linear Bandits with Memory","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2101.00001","title":"Etat de l'art sur l'application des bandits multi-bras","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2109.14733","title":"Batched Bandits with Crowd Externalities","created":"2021-09-29","cited_by_count":0,"area":null},{"id":"2111.13026","title":"Bandit problems with fidelity rewards","created":"2021-11-25","cited_by_count":0,"area":null},{"id":"2508.20923","title":"Finite-Time Guarantees for Multi-Agent Combinatorial Bandits with Nonstationary Rewards","created":"2025-08-28","cited_by_count":0,"area":null}],"next_cursor":null}