{"total":23,"rows":[{"id":"2110.13891","title":"Dynamic Causal Bayesian Optimization","created":"2021-10-26","cited_by_count":17,"area":null},{"id":"2307.05341","title":"Tracking Most Significant Shifts in Nonparametric Contextual Bandits","created":"2023-07-11","cited_by_count":10,"area":null},{"id":"2308.08497","title":"HyperBandit: Contextual Bandit with Hypernewtork for Time-Varying User Preferences in Streaming Recommendation","created":"2023-08-14","cited_by_count":10,"area":null},{"id":"2207.05742","title":"Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning","created":"2022-07-12","cited_by_count":9,"area":null},{"id":"2302.12202","title":"A Definition of Non-Stationary Bandits","created":"2023-02-23","cited_by_count":9,"area":null},{"id":"2311.05794","title":"An Experimental Design for Anytime-Valid Causal Inference on Multi-Armed Bandits","created":"2023-11-09","cited_by_count":9,"area":null},{"id":"2106.10935","title":"On Limited-Memory Subsampling Strategies for Bandits","created":"2021-06-21","cited_by_count":8,"area":null},{"id":"2210.14322","title":"ANACONDA: An Improved Dynamic Regret Algorithm for Adaptive Non-Stationary Dueling Bandits","created":"2022-10-25","cited_by_count":8,"area":null},{"id":"2308.07760","title":"Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender System","created":"2023-08-15","cited_by_count":7,"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":"2301.05492","title":"Disentangled Representation for Diversified Recommendations","created":"2023-01-13","cited_by_count":4,"area":null},{"id":"2305.10718","title":"Discounted Thompson Sampling for Non-Stationary Bandit Problems","created":"2023-05-18","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":"2301.00241","title":"Contextual Bandits and Optimistically Universal Learning","created":"2022-12-31","cited_by_count":2,"area":null},{"id":"2410.02126","title":"BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scale","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2105.14422","title":"Periodic-GP: Learning Periodic World with Gaussian Process Bandits","created":"2021-05-30","cited_by_count":1,"area":null},{"id":"2312.07285","title":"Forced Exploration in Bandit Problems","created":"2023-12-12","cited_by_count":1,"area":null},{"id":"2104.07150","title":"When and Whom to Collaborate with in a Changing Environment: A Collaborative Dynamic Bandit Solution","created":"2021-04-14","cited_by_count":0,"area":null},{"id":"2206.00861","title":"Dynamic Structure Estimation from Bandit Feedback using Nonvanishing Exponential Sums","created":"2022-06-02","cited_by_count":0,"area":null},{"id":"2307.09388","title":"Online Learning with Costly Features in Non-stationary Environments","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2311.09483","title":"Adaptive Interventions with User-Defined Goals for Health Behavior Change","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2403.00036","title":"Influencing Bandits: Arm Selection for Preference Shaping","created":"2024-02-29","cited_by_count":0,"area":null},{"id":"2604.08149","title":"A Direct Approach for Handling Contextual Bandits with Latent State Dynamics","created":"2026-04-09","cited_by_count":0,"area":null}],"next_cursor":null}