{"total":27,"rows":[{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120,"area":null},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2103.01133","title":"Posterior Meta-Replay for Continual Learning","created":"2021-03-01","cited_by_count":45,"area":null},{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45,"area":null},{"id":"2302.09205","title":"Approximate Thompson Sampling via Epistemic Neural Networks","created":"2023-02-18","cited_by_count":31,"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":"2110.04629","title":"The Neural Testbed: Evaluating Joint Predictions","created":"2021-10-09","cited_by_count":22,"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":"2305.17783","title":"Visual Affordance Prediction for Guiding Robot Exploration","created":"2023-05-28","cited_by_count":14,"area":null},{"id":"2306.14834","title":"Scalable Neural Contextual Bandit for Recommender Systems","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2202.13509","title":"Evaluating High-Order Predictive Distributions in Deep Learning","created":"2022-02-28","cited_by_count":10,"area":null},{"id":"2207.01524","title":"Variational Neural Networks","created":"2022-07-04","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":"2210.16877","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","created":"2022-10-30","cited_by_count":6,"area":null},{"id":"2304.05365","title":"Did we personalize? Assessing personalization by an online reinforcement learning algorithm using resampling","created":"2023-04-11","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":"2302.03439","title":"Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning","created":"2023-02-07","cited_by_count":5,"area":null},{"id":"2211.15931","title":"Posterior Sampling for Continuing Environments","created":"2022-11-29","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":"2206.09182","title":"Coin Flipping Neural Networks","created":"2022-06-18","cited_by_count":3,"area":null},{"id":"2210.04882","title":"Layer Ensembles","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2401.13657","title":"Inadequacy of common stochastic neural networks for reliable clinical decision support","created":"2024-01-24","cited_by_count":2,"area":null},{"id":"2402.10232","title":"Simple, unified analysis of Johnson-Lindenstrauss with applications","created":"2024-02-10","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}],"next_cursor":null}