{"total":53,"rows":[{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120,"area":null},{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45,"area":null},{"id":"2110.03177","title":"EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits","created":"2021-10-07","cited_by_count":44,"area":null},{"id":"2206.07659","title":"Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity","created":"2022-06-15","cited_by_count":32,"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":"2203.01303","title":"An Analysis of Ensemble Sampling","created":"2022-03-02","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":"2105.14267","title":"Information Directed Sampling for Sparse Linear Bandits","created":"2021-05-29","cited_by_count":20,"area":null},{"id":"2305.18258","title":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","created":"2023-05-29","cited_by_count":20,"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":"2206.03633","title":"Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping","created":"2022-06-08","cited_by_count":19,"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":"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":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2311.07565","title":"Exploration via linearly perturbed loss minimisation","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2401.02650","title":"Improving sample efficiency of high dimensional Bayesian optimization with MCMC","created":"2024-01-05","cited_by_count":9,"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":"2110.11202","title":"Anti-Concentrated Confidence Bonuses for Scalable Exploration","created":"2021-10-21","cited_by_count":7,"area":null},{"id":"2210.05770","title":"Deep Active Ensemble Sampling For Image Classification","created":"2022-10-11","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":"2311.08376","title":"Ensemble sampling for linear bandits: small ensembles suffice","created":"2023-11-14","cited_by_count":7,"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":"2411.03932","title":"Improved Regret of Linear Ensemble Sampling","created":"2024-11-06","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":"2601.22538","title":"Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Models","created":"2026-01-30","cited_by_count":6,"area":null},{"id":"2209.07676","title":"Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning","created":"2022-09-16","cited_by_count":5,"area":null},{"id":"2306.08803","title":"Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2506.11831","title":"Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2402.06963","title":"Tree Ensembles for Contextual Bandits","created":"2024-02-10","cited_by_count":4,"area":null},{"id":"2110.15907","title":"Learning to Be Cautious","created":"2021-10-29","cited_by_count":3,"area":null},{"id":"2302.01543","title":"Multiplier Bootstrap-based Exploration","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2201.12955","title":"Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework","created":"2022-01-31","cited_by_count":2,"area":null},{"id":"2203.13151","title":"Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic masking","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2310.18617","title":"Pessimistic Off-Policy Multi-Objective Optimization","created":"2023-10-28","cited_by_count":2,"area":null},{"id":"2501.04757","title":"Distance-Aware Error for Spline Networks: A Bottom-Up Approach to Uncertainty","created":"2025-01-08","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":"2602.06014","title":"Optimism Stabilizes Thompson Sampling for Adaptive Inference","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2103.04387","title":"CORe: Capitalizing On Rewards in Bandit Exploration","created":"2021-03-07","cited_by_count":1,"area":null},{"id":"2112.07007","title":"Optimizing over an ensemble of neural networks","created":"2021-12-13","cited_by_count":1,"area":null},{"id":"2203.08082","title":"Regenerative Particle Thompson Sampling","created":"2022-03-15","cited_by_count":1,"area":null},{"id":"2205.00163","title":"Deep Ensemble as a Gaussian Process Approximate Posterior","created":"2022-04-30","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":"2505.16311","title":"Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2510.05023","title":"Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspective","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2602.08026","title":"Sharp analysis of linear ensemble sampling","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2105.02569","title":"Machine Collaboration","created":"2021-05-06","cited_by_count":0,"area":null},{"id":"2303.04115","title":"Predicted Embedding Power Regression for Large-Scale Out-of-Distribution Detection","created":"2023-03-07","cited_by_count":0,"area":null},{"id":"2406.14071","title":"Bayesian Bandit Algorithms with Approximate Inference in Stochastic Linear Bandits","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2609.13954","title":"Linear Ensemble Sampling with Smaller Ensembles","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}