{"total":24,"rows":[{"id":"2307.13372","title":"Submodular Reinforcement Learning","created":"2023-07-25","cited_by_count":23,"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":"2205.14790","title":"Non-Stationary Bandits under Recharging Payoffs: Improved Planning with Sublinear Regret","created":"2022-05-29","cited_by_count":5,"area":null},{"id":"2406.05187","title":"How to Strategize Human Content Creation in the Era of GenAI?","created":"2024-06-07","cited_by_count":4,"area":null},{"id":"2105.10625","title":"Combinatorial Blocking Bandits with Stochastic Delays","created":"2021-05-22","cited_by_count":3,"area":null},{"id":"2204.11174","title":"Complete Policy Regret Bounds for Tallying Bandits","created":"2022-04-24","cited_by_count":3,"area":null},{"id":"2306.00338","title":"Last Switch Dependent Bandits with Monotone Payoff Functions","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2102.00321","title":"Recurrent Submodular Welfare and Matroid Blocking Bandits","created":"2021-01-30","cited_by_count":2,"area":null},{"id":"2209.04147","title":"Extending Open Bandit Pipeline to Simulate Industry Challenges","created":"2022-09-09","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":"2307.11655","title":"Preferences Evolve And So Should Your Bandits: Bandits with Evolving States for Online Platforms","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2510.16208","title":"Explore-then-Commit for Nonstationary Linear Bandits with Latent Dynamics","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2304.09088","title":"A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed Bandits","created":"2023-04-16","cited_by_count":1,"area":null},{"id":"2410.21266","title":"Online Weighted Paging with Unknown Weights","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2509.20304","title":"Ads that Stick: Near-Optimal Ad Optimization through Psychological Behavior Models","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2603.19700","title":"Regret Analysis of Sleeping Competing Bandits","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2608.15848","title":"Generalized Linear Bandits with Memory","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2106.14813","title":"Offline Planning and Online Learning under Recovering Rewards","created":"2021-06-28","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":"2301.03099","title":"Fully Dynamic Online Selection through Online Contention Resolution Schemes","created":"2023-01-08","cited_by_count":0,"area":null},{"id":"2504.08200","title":"Influential Bandits: Pulling an Arm May Change the Environment","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2606.27448","title":"Learning in Markovian bandits with non-observable states and constrained decision epochs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2610.00911","title":"Block Optimism for Nonstationary Bandits with Latent Linear Dynamics","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}