{"total":71,"rows":[{"id":"2110.03177","title":"EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits","created":"2021-10-07","cited_by_count":44,"area":null},{"id":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"area":null},{"id":"2403.05171","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","created":"2024-03-08","cited_by_count":33,"area":"alignment"},{"id":"2111.13807","title":"Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization","created":"2021-11-27","cited_by_count":25,"area":"offlinerl"},{"id":"2210.06850","title":"Sample-Then-Optimize Batch Neural Thompson Sampling","created":"2022-10-13","cited_by_count":25,"area":null},{"id":"2102.13028","title":"Batched Neural Bandits","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2206.11254","title":"Langevin Monte Carlo for Contextual Bandits","created":"2022-06-22","cited_by_count":22,"area":null},{"id":"2505.16270","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","created":"2025-05-22","cited_by_count":21,"area":null},{"id":"2201.09910","title":"Learning Neural Contextual Bandits Through Perturbed Rewards","created":"2022-01-24","cited_by_count":17,"area":null},{"id":"2205.14309","title":"Federated Neural Bandits","created":"2022-05-28","cited_by_count":17,"area":null},{"id":"2107.04518","title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2102.03799","title":"Online Limited Memory Neural-Linear Bandits with Likelihood Matching","created":"2021-02-07","cited_by_count":14,"area":null},{"id":"2109.12509","title":"Deep Exploration for Recommendation Systems","created":"2021-09-26","cited_by_count":14,"area":null},{"id":"2411.01410","title":"PageRank Bandits for Link Prediction","created":"2024-11-03","cited_by_count":14,"area":null},{"id":"2601.22664","title":"Real-Time Aligned Reward Model beyond Semantics","created":"2026-01-30","cited_by_count":13,"area":"alignment"},{"id":"2306.14834","title":"Scalable Neural Contextual Bandit for Recommender Systems","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2209.06129","title":"Hierarchical Conversational Preference Elicitation with Bandit Feedback","created":"2022-09-06","cited_by_count":10,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2309.08634","title":"Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2304.02572","title":"Evaluating Online Bandit Exploration In Large-Scale Recommender System","created":"2023-04-05","cited_by_count":7,"area":null},{"id":"2305.03784","title":"Neural Exploitation and Exploration of Contextual Bandits","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2408.05586","title":"Meta Clustering of Neural Bandits","created":"2024-08-10","cited_by_count":7,"area":null},{"id":"2207.12805","title":"Neural Design for Genetic Perturbation Experiments","created":"2022-07-26","cited_by_count":6,"area":null},{"id":"2307.10167","title":"VITS : Variational Inference Thompson Sampling for contextual bandits","created":"2023-07-19","cited_by_count":6,"area":null},{"id":"2405.03059","title":"Active Preference Learning for Ordering Items In- and Out-of-sample","created":"2024-05-05","cited_by_count":6,"area":null},{"id":"2505.02069","title":"Neural Logistic Bandits","created":"2025-05-04","cited_by_count":6,"area":null},{"id":"2210.13083","title":"Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2305.19922","title":"Representation-Driven Reinforcement Learning","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2504.12016","title":"Active Human Feedback Collection via Neural Contextual Dueling Bandits","created":"2025-04-16","cited_by_count":4,"area":"alignment"},{"id":"2507.15290","title":"Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown","created":"2025-07-21","cited_by_count":4,"area":null},{"id":"2112.02185","title":"Neural Pseudo-Label Optimism for the Bank Loan Problem","created":"2021-12-03","cited_by_count":3,"area":null},{"id":"2303.06389","title":"Uncertainty-Aware Instance Reweighting for Off-Policy Learning","created":"2023-03-11","cited_by_count":3,"area":null},{"id":"2401.06173","title":"Tree Search-Based Evolutionary Bandits for Protein Sequence Optimization","created":"2024-01-08","cited_by_count":3,"area":null},{"id":"2402.05002","title":"Randomized Confidence Bounds for Stochastic Partial Monitoring","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2405.04393","title":"Efficient Online Set-valued Classification with Bandit Feedback","created":"2024-05-07","cited_by_count":3,"area":null},{"id":"2411.05979","title":"Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits","created":"2024-11-08","cited_by_count":3,"area":null},{"id":"2502.02079","title":"Online Clustering of Dueling Bandits","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2203.04192","title":"Reward-Biased Maximum Likelihood Estimation for Neural Contextual Bandits","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2206.14648","title":"Two-Stage Neural Contextual Bandits for Personalised News Recommendation","created":"2022-06-26","cited_by_count":2,"area":null},{"id":"2303.01682","title":"Neural-BO: A Black-box Optimization Algorithm using Deep Neural Networks","created":"2023-03-03","cited_by_count":2,"area":null},{"id":"2405.07331","title":"Stochastic Bandits with ReLU Neural Networks","created":"2024-05-12","cited_by_count":2,"area":null},{"id":"2407.00567","title":"A Contextual Combinatorial Bandit Approach to Negotiation","created":"2024-06-30","cited_by_count":2,"area":null},{"id":"2408.07647","title":"Adaptive Behavioral AI: Reinforcement Learning to Enhance Pharmacy Services","created":"2024-08-14","cited_by_count":2,"area":null},{"id":"2506.01250","title":"Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2510.10730","title":"Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2111.03543","title":"Empirical analysis of representation learning and exploration in neural kernel bandits","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2310.07786","title":"Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2312.09961","title":"Risk-Aware Continuous Control with Neural Contextual Bandits","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2403.06814","title":"{\\epsilon}-Neural Thompson Sampling of Deep Brain Stimulation for Parkinson Disease Treatment","created":"2024-03-11","cited_by_count":1,"area":null},{"id":"2405.08921","title":"Neural Active Learning Meets the Partial Monitoring Framework","created":"2024-05-14","cited_by_count":1,"area":null},{"id":"2406.02515","title":"Uncertainty of Joint Neural Contextual Bandit","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2406.09564","title":"Towards Domain Adaptive Neural Contextual Bandits","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2406.10686","title":"Graph Neural Thompson Sampling","created":"2024-06-15","cited_by_count":1,"area":null},{"id":"2409.16098","title":"The Digital Transformation in Health: How AI Can Improve the Performance of Health Systems","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2412.04484","title":"Epinet for Content Cold Start","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2503.18980","title":"CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning","created":"2025-03-23","cited_by_count":1,"area":"deeprl"},{"id":"2506.12389","title":"Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2601.20666","title":"Learning Contextual Runtime Monitors for Safe AI-Based Autonomy","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2607.22518","title":"PinEqualizer: Full Funnel Content Exploration and Debiasing System at Pinterest","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2609.11682","title":"COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization","created":"2026-09-10","cited_by_count":1,"area":"agents"},{"id":"2308.08051","title":"Unbiased Decisions Reduce Regret: Adversarial Domain Adaptation for the Bank Loan Problem","created":"2023-08-15","cited_by_count":0,"area":null},{"id":"2402.08769","title":"FLASH: Federated Learning Across Simultaneous Heterogeneities","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2408.07629","title":"Optimizing HIV Patient Engagement with Reinforcement Learning in Resource-Limited Settings","created":"2024-08-14","cited_by_count":0,"area":null},{"id":"2408.08024","title":"Adaptive User Journeys in Pharma E-Commerce with Reinforcement Learning: Insights from SwipeRx","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2412.00569","title":"Contextual Bandits in Payment Processing: Non-uniform Exploration and Supervised Learning","created":"2024-11-30","cited_by_count":0,"area":null},{"id":"2501.11265","title":"A Metric Topology of Deep Learning for Data Classification","created":"2025-01-20","cited_by_count":0,"area":null},{"id":"2504.12086","title":"Neural Contextual Bandits Under Delayed Feedback Constraints","created":"2025-04-16","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":"2601.06913","title":"Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2603.00567","title":"Learning to Attack: A Bandit Approach to Adversarial Context Poisoning","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2607.26599","title":"Uncertainty-Guided LLM Semantic Augmentation for Heterogeneous Treatment Effect Estimation","created":"2026-07-29","cited_by_count":0,"area":null}],"next_cursor":null}