{"total":17,"rows":[{"id":"2410.13287","title":"PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMs","created":"2024-10-17","cited_by_count":12,"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":"2312.01457","title":"Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits","created":"2023-12-03","cited_by_count":9,"area":null},{"id":"2105.00822","title":"Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference","created":"2021-05-03","cited_by_count":6,"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":"2201.07681","title":"Learning to Rank For Push Notifications Using Pairwise Expected Regret","created":"2022-01-19","cited_by_count":3,"area":null},{"id":"2202.11735","title":"Truncated LinUCB for Stochastic Linear Bandits","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2210.06302","title":"Maximum entropy exploration in contextual bandits with neural networks and energy based models","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2307.09093","title":"Non-stationary Delayed Combinatorial Semi-Bandit with Causally Related Rewards","created":"2023-07-18","cited_by_count":1,"area":null},{"id":"2208.04822","title":"Generalized Reinforcement Learning: Experience Particles, Action Operator, Reinforcement Field, Memory Association, and Decision Concepts","created":"2022-08-09","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":"2410.05734","title":"Diminishing Exploration: A Minimalist Approach to Piecewise Stationary Multi-Armed Bandits","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2411.05661","title":"Multi-armed Bandits with Missing Outcome","created":"2024-11-08","cited_by_count":0,"area":null},{"id":"2503.16107","title":"Learn to Bid as a Price-Maker Wind Power Producer","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2505.03840","title":"CoCoB: Adaptive Collaborative Combinatorial Bandits for Online Recommendation","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2507.18756","title":"Exploitation Over Exploration: Unmasking the Bias in Linear Bandit Recommender Offline Evaluation","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2605.31291","title":"Contextual Scalarisation Thompson Sampling for multi-objective decisions in public media","created":"2026-05-29","cited_by_count":0,"area":null}],"next_cursor":null}