{"total":160,"rows":[{"id":"2110.00871","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","created":"2021-10-02","cited_by_count":66,"area":null},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2107.01509","title":"Bayesian decision-making under misspecified priors with applications to meta-learning","created":"2021-07-03","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":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2107.09224","title":"From Predictions to Decisions: The Importance of Joint Predictive Distributions","created":"2021-07-20","cited_by_count":29,"area":null},{"id":"2206.01558","title":"Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning","created":"2022-06-03","cited_by_count":27,"area":null},{"id":"2203.01303","title":"An Analysis of Ensemble Sampling","created":"2022-03-02","cited_by_count":24,"area":null},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2101.06197","title":"Deciding What to Learn: A Rate-Distortion Approach","created":"2021-01-15","cited_by_count":23,"area":null},{"id":"2102.13202","title":"Online Multi-Armed Bandits with Adaptive Inference","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2310.19848","title":"Efficient Exploration in Continuous-time Model-based Reinforcement Learning","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2205.01970","title":"Non-Stationary Bandit Learning via Predictive Sampling","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","cited_by_count":20,"area":null},{"id":"2104.06970","title":"Understanding the Eluder Dimension","created":"2021-04-14","cited_by_count":19,"area":null},{"id":"2110.00202","title":"Batched Thompson Sampling","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2202.01454","title":"Deep Hierarchy in Bandits","created":"2022-02-03","cited_by_count":19,"area":null},{"id":"2205.13924","title":"Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits","created":"2022-05-27","cited_by_count":19,"area":null},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2310.00806","title":"Bayesian Design Principles for Frequentist Sequential Learning","created":"2023-10-01","cited_by_count":18,"area":null},{"id":"2307.09943","title":"Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay","created":"2023-07-19","cited_by_count":17,"area":null},{"id":"2409.05181","title":"Sliding-Window Thompson Sampling for Non-Stationary Settings","created":"2024-09-08","cited_by_count":17,"area":null},{"id":"2106.05608","title":"Thompson Sampling with a Mixture Prior","created":"2021-06-10","cited_by_count":16,"area":null},{"id":"2107.05320","title":"Metalearning Linear Bandits by Prior Update","created":"2021-07-12","cited_by_count":16,"area":null},{"id":"2110.13973","title":"The Value of Information When Deciding What to Learn","created":"2021-10-26","cited_by_count":15,"area":null},{"id":"2101.09855","title":"Weak Signal Asymptotics for Sequentially Randomized Experiments","created":"2021-01-25","cited_by_count":14,"area":null},{"id":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2211.08572","title":"Bayesian Fixed-Budget Best-Arm Identification","created":"2022-11-15","cited_by_count":13,"area":null},{"id":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2101.08699","title":"An empirical evaluation of active inference in multi-armed bandits","created":"2021-01-21","cited_by_count":12,"area":null},{"id":"2105.09232","title":"Diffusion Approximations for Thompson Sampling in the Small Gap Regime","created":"2021-05-19","cited_by_count":12,"area":null},{"id":"2209.14414","title":"Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2302.04452","title":"An Information-Theoretic Analysis of Nonstationary Bandit Learning","created":"2023-02-09","cited_by_count":11,"area":null},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2107.13078","title":"A Payload Optimization Method for Federated Recommender Systems","created":"2021-07-27","cited_by_count":10,"area":null},{"id":"2309.00591","title":"Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms","created":"2023-09-01","cited_by_count":10,"area":null},{"id":"2401.11665","title":"Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo","created":"2024-01-22","cited_by_count":10,"area":null},{"id":"2103.02729","title":"Linear Bandit Algorithms with Sublinear Time Complexity","created":"2021-03-03","cited_by_count":9,"area":null},{"id":"2107.00140","title":"Applications of the Free Energy Principle to Machine Learning and Neuroscience","created":"2021-06-30","cited_by_count":9,"area":null},{"id":"2206.00494","title":"Incentivizing Combinatorial Bandit Exploration","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2209.10715","title":"Batch Bayesian optimisation via density-ratio estimation with guarantees","created":"2022-09-22","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":"2404.02649","title":"On the Importance of Uncertainty in Decision-Making with Large Language Models","created":"2024-04-03","cited_by_count":9,"area":null},{"id":"2202.09036","title":"Adaptive Experimentation in the Presence of Exogenous Nonstationary Variation","created":"2022-02-18","cited_by_count":8,"area":null},{"id":"2409.07594","title":"Automated Discovery of Pairwise Interactions from Unstructured Data","created":"2024-09-11","cited_by_count":8,"area":null},{"id":"2502.08870","title":"When and why randomised exploration works (in linear bandits)","created":"2025-02-13","cited_by_count":8,"area":null},{"id":"2104.14113","title":"Regret Bounds for Gaussian-Process Optimization in Large Domains","created":"2021-04-29","cited_by_count":7,"area":null},{"id":"2107.02377","title":"A Short Note on the Relationship of Information Gain and Eluder Dimension","created":"2021-07-06","cited_by_count":7,"area":null},{"id":"2110.15688","title":"Variational Bayesian Optimistic Sampling","created":"2021-10-29","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":"2209.09655","title":"Lower Bounds on the Worst-Case Complexity of Efficient Global Optimization","created":"2022-09-20","cited_by_count":7,"area":null},{"id":"2310.20007","title":"Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2402.15411","title":"Optimistic Information Directed Sampling","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2504.04204","title":"Adaptive Elicitation of Latent Information Using Natural Language","created":"2025-04-05","cited_by_count":7,"area":null},{"id":"2202.12431","title":"Thompson Sampling with Unrestricted Delays","created":"2022-02-24","cited_by_count":6,"area":null},{"id":"2210.16877","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","created":"2022-10-30","cited_by_count":6,"area":null},{"id":"2302.11182","title":"When Combinatorial Thompson Sampling meets Approximation Regret","created":"2023-02-22","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":"2502.07064","title":"Contextual Thompson Sampling via Generation of Missing Data","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2510.13328","title":"Thompson Sampling via Fine-Tuning of LLMs","created":"2025-10-15","cited_by_count":6,"area":null},{"id":"2102.09488","title":"A Bit Better? Quantifying Information for Bandit Learning","created":"2021-02-18","cited_by_count":5,"area":null},{"id":"2102.10085","title":"Output-Weighted Sampling for Multi-Armed Bandits with Extreme Payoffs","created":"2021-02-19","cited_by_count":5,"area":null},{"id":"2103.05541","title":"Constrained Contextual Bandit Learning for Adaptive Radar Waveform Selection","created":"2021-03-09","cited_by_count":5,"area":null},{"id":"2201.01902","title":"Gaussian Imagination in Bandit Learning","created":"2022-01-06","cited_by_count":5,"area":null},{"id":"2209.02211","title":"Multi-Armed Bandits with Self-Information Rewards","created":"2022-09-06","cited_by_count":5,"area":null},{"id":"2304.13593","title":"Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards","created":"2023-04-26","cited_by_count":5,"area":null},{"id":"2410.22322","title":"Optimizing Posterior Samples for Bayesian Optimization via Rootfinding","created":"2024-10-29","cited_by_count":5,"area":null},{"id":"2505.07367","title":"Generalization Bounds and Stopping Rules for Learning with Self-Selected Data","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2505.23165","title":"Best Arm Identification with Possibly Biased Offline Data","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2301.12038","title":"STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning","created":"2023-01-28","cited_by_count":4,"area":null},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2402.10282","title":"Information Capacity Regret Bounds for Bandits with Mediator Feedback","created":"2024-02-15","cited_by_count":4,"area":null},{"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":"2105.01445","title":"Online Transfer Learning: Negative Transfer and Effect of Prior Knowledge","created":"2021-05-04","cited_by_count":3,"area":null},{"id":"2109.01377","title":"A Bayesian Approach to (Online) Transfer Learning: Theory and Algorithms","created":"2021-09-03","cited_by_count":3,"area":null},{"id":"2109.14412","title":"Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification","created":"2021-09-29","cited_by_count":3,"area":null},{"id":"2110.00158","title":"Asymptotic Performance of Thompson Sampling in the Batched Multi-Armed Bandits","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2203.00820","title":"Partial Likelihood Thompson Sampling","created":"2022-03-02","cited_by_count":3,"area":null},{"id":"2207.14419","title":"Sample-efficient Safe Learning for Online Nonlinear Control with Control Barrier Functions","created":"2022-07-29","cited_by_count":3,"area":null},{"id":"2302.01544","title":"Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2303.09033","title":"Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling","created":"2023-03-16","cited_by_count":3,"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":"2405.16581","title":"On Bits and Bandits: Quantifying the Regret-Information Trade-off","created":"2024-05-26","cited_by_count":3,"area":null},{"id":"2501.13535","title":"LITE: Efficiently Estimating Gaussian Probability of Maximality","created":"2025-01-23","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":"2205.14829","title":"Adaptive Sampling for Discovery","created":"2022-05-30","cited_by_count":2,"area":null},{"id":"2301.12822","title":"Evaluating COVID-19 vaccine allocation policies using Bayesian $m$-top exploration","created":"2023-01-30","cited_by_count":2,"area":null},{"id":"2302.06916","title":"Effective Dimension in Bandit Problems under Censorship","created":"2023-02-14","cited_by_count":2,"area":null},{"id":"2305.00403","title":"Optimal tests following sequential experiments","created":"2023-04-30","cited_by_count":2,"area":null},{"id":"2305.02093","title":"Efficient Online Decision Tree Learning with Active Feature Acquisition","created":"2023-05-03","cited_by_count":2,"area":null},{"id":"2311.14359","title":"Thompson sampling for zero-inflated count outcomes with an application to the Drink Less mobile health study","created":"2023-11-24","cited_by_count":2,"area":null},{"id":"2401.11565","title":"Thompson Sampling for Stochastic Bandits with Noisy Contexts: An Information-Theoretic Regret Analysis","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2402.13338","title":"Incentivized Exploration via Filtered Posterior Sampling","created":"2024-02-20","cited_by_count":2,"area":null},{"id":"2403.10379","title":"Regret Minimization via Saddle Point Optimization","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2404.07266","title":"Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2409.16632","title":"Functional Stochastic Gradient MCMC for Bayesian Neural Networks","created":"2024-09-25","cited_by_count":2,"area":null},{"id":"2410.15543","title":"Distributed Thompson sampling under constrained communication","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2503.00273","title":"Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2510.01620","title":"Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2602.06014","title":"Optimism Stabilizes Thompson Sampling for Adaptive Inference","created":"2026-02-05","cited_by_count":2,"area":null}],"next_cursor":"100"}