{"total":177,"rows":[{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164,"area":"offlinerl"},{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81,"area":null},{"id":"2110.14177","title":"Federated Linear Contextual Bandits","created":"2021-10-27","cited_by_count":61,"area":null},{"id":"2110.07788","title":"Gaussian Process Bandit Optimization with Few Batches","created":"2021-10-15","cited_by_count":57,"area":null},{"id":"2105.05806","title":"High-Dimensional Experimental Design and Kernel Bandits","created":"2021-05-12","cited_by_count":56,"area":null},{"id":"2111.05008","title":"Misspecified Gaussian Process Bandit Optimization","created":"2021-11-09","cited_by_count":55,"area":null},{"id":"2108.09262","title":"Optimal Order Simple Regret for Gaussian Process Bandits","created":"2021-08-20","cited_by_count":54,"area":null},{"id":"2402.16359","title":"Feedback Efficient Online Fine-Tuning of Diffusion Models","created":"2024-02-26","cited_by_count":53,"area":"diffusion"},{"id":"2110.03177","title":"EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits","created":"2021-10-07","cited_by_count":44,"area":null},{"id":"2107.03144","title":"Neural Contextual Bandits without Regret","created":"2021-07-07","cited_by_count":40,"area":null},{"id":"2202.04593","title":"Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models","created":"2022-02-09","cited_by_count":37,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2106.03207","title":"Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage","created":"2021-06-06","cited_by_count":26,"area":"offlinerl"},{"id":"2307.07539","title":"On the Sublinear Regret of GP-UCB","created":"2023-07-14","cited_by_count":26,"area":null},{"id":"2111.13807","title":"Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization","created":"2021-11-27","cited_by_count":25,"area":"offlinerl"},{"id":"2405.19673","title":"Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models","created":"2024-05-30","cited_by_count":25,"area":"diffusion"},{"id":"2203.15589","title":"On Kernelized Multi-Armed Bandits with Constraints","created":"2022-03-29","cited_by_count":23,"area":null},{"id":"2102.13028","title":"Batched Neural Bandits","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2106.03243","title":"Neural Active Learning with Performance Guarantees","created":"2021-06-06","cited_by_count":22,"area":null},{"id":"2109.06099","title":"Uniform Generalization Bounds for Overparameterized Neural Networks","created":"2021-09-13","cited_by_count":21,"area":null},{"id":"2106.03039","title":"Multi-facet Contextual Bandits: A Neural Network Perspective","created":"2021-06-06","cited_by_count":20,"area":null},{"id":"2110.09771","title":"On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game","created":"2021-10-19","cited_by_count":20,"area":null},{"id":"2306.07745","title":"Kernelized Reinforcement Learning with Order Optimal Regret Bounds","created":"2023-06-13","cited_by_count":20,"area":null},{"id":"2308.10808","title":"Graph Neural Bandits","created":"2023-08-21","cited_by_count":20,"area":null},{"id":"2202.04005","title":"Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning","created":"2022-02-08","cited_by_count":18,"area":null},{"id":"2111.01768","title":"Nearly Optimal Algorithms for Level Set Estimation","created":"2021-11-02","cited_by_count":17,"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":"2205.14775","title":"An Optimization-based Algorithm for Non-stationary Kernel Bandits without Prior Knowledge","created":"2022-05-29","cited_by_count":17,"area":null},{"id":"2310.15351","title":"Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency","created":"2023-10-23","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":"2203.07875","title":"Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization","created":"2022-03-15","cited_by_count":15,"area":null},{"id":"2206.04835","title":"Communication Efficient Distributed Learning for Kernelized Contextual Bandits","created":"2022-06-10","cited_by_count":15,"area":null},{"id":"2212.08765","title":"Latent Variable Representation for Reinforcement Learning","created":"2022-12-17","cited_by_count":15,"area":null},{"id":"2502.06363","title":"Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance","created":"2025-02-10","cited_by_count":15,"area":null},{"id":"2103.10369","title":"Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning","created":"2021-03-18","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":"2106.12034","title":"Pure Exploration in Kernel and Neural Bandits","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2110.15458","title":"Open Problem: Tight Online Confidence Intervals for RKHS Elements","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2110.15771","title":"Collaborative Pure Exploration in Kernel Bandit","created":"2021-10-29","cited_by_count":13,"area":null},{"id":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"id":"2505.14661","title":"Abacus: A Cost-Based Optimizer for Semantic Operator Systems","created":"2025-05-20","cited_by_count":13,"area":null},{"id":"2506.01393","title":"Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2102.05793","title":"Lenient Regret and Good-Action Identification in Gaussian Process Bandits","created":"2021-02-11","cited_by_count":12,"area":null},{"id":"2206.12081","title":"Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings","created":"2022-06-24","cited_by_count":12,"area":null},{"id":"2302.03683","title":"Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2309.14298","title":"Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures","created":"2023-09-25","cited_by_count":12,"area":null},{"id":"2310.05373","title":"Quantum Bayesian Optimization","created":"2023-10-09","cited_by_count":12,"area":null},{"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":"2210.00423","title":"Improved Algorithms for Neural Active Learning","created":"2022-10-02","cited_by_count":11,"area":null},{"id":"2206.09341","title":"Bayesian Optimization under Stochastic Delayed Feedback","created":"2022-06-19","cited_by_count":10,"area":null},{"id":"2207.06456","title":"Graph Neural Network Bandits","created":"2022-07-13","cited_by_count":10,"area":null},{"id":"2302.00392","title":"Delayed Feedback in Kernel Bandits","created":"2023-02-01","cited_by_count":10,"area":null},{"id":"2312.14037","title":"Neural Contextual Bandits for Personalized Recommendation","created":"2023-12-21","cited_by_count":10,"area":null},{"id":"2406.05064","title":"Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning","created":"2024-06-07","cited_by_count":10,"area":"offlinerl"},{"id":"2207.11597","title":"Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference","created":"2022-07-23","cited_by_count":9,"area":null},{"id":"2502.19006","title":"Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2102.05018","title":"Robust Bandit Learning with Imperfect Context","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2206.03644","title":"Neural Bandit with Arm Group Graph","created":"2022-06-08","cited_by_count":8,"area":null},{"id":"2303.07154","title":"Differential Good Arm Identification","created":"2023-03-13","cited_by_count":8,"area":null},{"id":"2403.12732","title":"Tighter Confidence Bounds for Sequential Kernel Regression","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2106.08598","title":"Ada-BKB: Scalable Gaussian Process Optimization on Continuous Domains by Adaptive Discretization","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2201.13395","title":"Neural Collaborative Filtering Bandits via Meta Learning","created":"2022-01-31","cited_by_count":7,"area":null},{"id":"2202.08867","title":"Fast online inference for nonlinear contextual bandit based on Generative Adversarial Network","created":"2022-02-17","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":"2306.06291","title":"Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2311.02715","title":"Exploiting Correlated Auxiliary Feedback in Parameterized Bandits","created":"2023-11-05","cited_by_count":7,"area":null},{"id":"2406.16745","title":"Bandits with Preference Feedback: A Stackelberg Game Perspective","created":"2024-06-24","cited_by_count":7,"area":"alignment"},{"id":"2407.17112","title":"Neural Dueling Bandits: Preference-Based Optimization with Human Feedback","created":"2024-07-24","cited_by_count":7,"area":"alignment"},{"id":"2408.05586","title":"Meta Clustering of Neural Bandits","created":"2024-08-10","cited_by_count":7,"area":null},{"id":"2203.02605","title":"Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions","created":"2022-03-04","cited_by_count":6,"area":null},{"id":"2205.04901","title":"Adjusted Expected Improvement for Cumulative Regret Minimization in Noisy Bayesian Optimization","created":"2022-05-10","cited_by_count":6,"area":null},{"id":"2206.00099","title":"Provably and Practically Efficient Neural Contextual Bandits","created":"2022-05-31","cited_by_count":6,"area":null},{"id":"2207.07948","title":"Collaborative Learning in Kernel-based Bandits for Distributed Users","created":"2022-07-16","cited_by_count":6,"area":null},{"id":"2302.12120","title":"Sequential Counterfactual Risk Minimization","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2310.01609","title":"Adversarial Contextual Bandits Go Kernelized","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2404.17493","title":"Causally Abstracted Multi-armed Bandits","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2410.23498","title":"Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm","created":"2024-10-30","cited_by_count":6,"area":"deeprl"},{"id":"2505.02069","title":"Neural Logistic Bandits","created":"2025-05-04","cited_by_count":6,"area":null},{"id":"2605.20552","title":"Spectral bandits for smooth graph functions with applications in recommender systems","created":"2026-05-19","cited_by_count":6,"area":null},{"id":"2203.06297","title":"Instance-Dependent Regret Analysis of Kernelized Bandits","created":"2022-03-12","cited_by_count":5,"area":null},{"id":"2210.06719","title":"Reward Imputation with Sketching for Contextual Batched Bandits","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2304.13830","title":"Adaptation to Misspecified Kernel Regularity in Kernelised Bandits","created":"2023-04-26","cited_by_count":5,"area":null},{"id":"2306.00096","title":"Learning the Pareto Front Using Bootstrapped Observation Samples","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2405.08498","title":"Learning Decision Policies with Instrumental Variables through Double Machine Learning","created":"2024-05-14","cited_by_count":5,"area":null},{"id":"2410.16692","title":"Lower Bounds for Time-Varying Kernelized Bandits","created":"2024-10-22","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":"2204.10349","title":"Provably Efficient Kernelized Q-Learning","created":"2022-04-21","cited_by_count":4,"area":null},{"id":"2210.15513","title":"Lifelong Bandit Optimization: No Prior and No Regret","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2305.00322","title":"Toward $L_\\infty$-recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields","created":"2023-04-29","cited_by_count":4,"area":null},{"id":"2406.12835","title":"Influence Maximization via Graph Neural Bandits","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2410.16972","title":"Sample-efficient Bayesian Optimisation Using Known Invariances","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2508.01681","title":"Generalized Kernelized Bandits: A Novel Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Bounds","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2602.17940","title":"Tighter Regret Lower Bound for Gaussian Process Bandits with Squared Exponential Kernel in Hypersphere","created":"2026-02-20","cited_by_count":4,"area":null},{"id":"2109.07275","title":"DROMO: Distributionally Robust Offline Model-based Policy Optimization","created":"2021-09-15","cited_by_count":3,"area":"offlinerl"},{"id":"2202.05638","title":"Efficient Kernel UCB for Contextual Bandits","created":"2022-02-11","cited_by_count":3,"area":null},{"id":"2302.12780","title":"VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation","created":"2023-02-24","cited_by_count":3,"area":"offlinerl"},{"id":"2305.01063","title":"Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making","created":"2023-05-02","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":"2501.07046","title":"Differentially Private Kernelized Contextual Bandits","created":"2025-01-13","cited_by_count":3,"area":null}],"next_cursor":"100"}