{"total":31,"rows":[{"id":"2302.06873","title":"Lero: A Learning-to-Rank Query Optimizer","created":"2023-02-14","cited_by_count":26,"area":null},{"id":"2108.06422","title":"Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models","created":"2021-08-13","cited_by_count":24,"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":"2211.15823","title":"Personalized Reward Learning with Interaction-Grounded Learning (IGL)","created":"2022-11-28","cited_by_count":9,"area":null},{"id":"2305.03954","title":"Learning Action Embeddings for Off-Policy Evaluation","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2403.15640","title":"Contextual Restless Multi-Armed Bandits with Application to Demand Response Decision-Making","created":"2024-03-22","cited_by_count":7,"area":null},{"id":"2106.13895","title":"Knowledge Infused Policy Gradients with Upper Confidence Bound for Relational Bandits","created":"2021-06-25","cited_by_count":6,"area":null},{"id":"2312.15999","title":"Pricing with Contextual Elasticity and Heteroscedastic Valuation","created":"2023-12-26","cited_by_count":5,"area":null},{"id":"2106.13539","title":"Dealing with Expert Bias in Collective Decision-Making","created":"2021-06-25","cited_by_count":4,"area":null},{"id":"2110.15501","title":"Doubly Robust Interval Estimation for Optimal Policy Evaluation in Online Learning","created":"2021-10-29","cited_by_count":4,"area":null},{"id":"2201.12700","title":"Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms","created":"2022-01-30","cited_by_count":4,"area":null},{"id":"2306.14872","title":"Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2307.01563","title":"Approximate information for efficient exploration-exploitation strategies","created":"2023-07-04","cited_by_count":2,"area":null},{"id":"2402.10192","title":"Multi-Excitation Projective Simulation with a Many-Body Physics Inspired Inductive Bias","created":"2024-02-15","cited_by_count":2,"area":null},{"id":"2209.06128","title":"A Scalable Recommendation Engine for New Users and Items","created":"2022-09-06","cited_by_count":1,"area":null},{"id":"2210.13692","title":"Sequential Decision Making on Unmatched Data using Bayesian Kernel Embeddings","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2410.17216","title":"Hierarchical Upper Confidence Bounds for Constrained Online Learning","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2605.27073","title":"Learning to Orchestrate Agents under Uncertainty","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2310.01419","title":"Design Principles of Robust Multi-Armed Bandit Framework in Video Recommendations","created":"2023-09-24","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":"2408.06257","title":"Reciprocal Learning","created":"2024-08-12","cited_by_count":0,"area":null},{"id":"2412.18845","title":"Enhancing Federated Graph Learning via Adaptive Fusion of Structural and Node Characteristics","created":"2024-12-25","cited_by_count":0,"area":null},{"id":"2503.15962","title":"Information maximization for a broad variety of multi-armed bandit games","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2505.15069","title":"In-Domain African Languages Translation Using LLMs and Multi-armed Bandits","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2505.16918","title":"Scalable and Interpretable Contextual Bandits: A Literature Review and Retail Offer Prototype","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2506.13730","title":"BanditWare: A Contextual Bandit-based Framework for Hardware Prediction","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2508.05367","title":"Latent Preference Bandits","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2602.04181","title":"Piece of CAKE: Adaptive Execution Engines via Microsecond-Scale Learning","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.18431","title":"Towards Noise-Resilient Quantum Multi-Armed and Stochastic Linear Bandits","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.30035","title":"Reward-Based Online LLM Routing via NeuralUCB","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.07304","title":"Latent Order Bandits","created":"2026-05-08","cited_by_count":0,"area":null}],"next_cursor":null}