{"total":32,"rows":[{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2402.03563","title":"Distinguishing the Knowable from the Unknowable with Language Models","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2302.09205","title":"Approximate Thompson Sampling via Epistemic Neural Networks","created":"2023-02-18","cited_by_count":31,"area":null},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"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":"2110.04629","title":"The Neural Testbed: Evaluating Joint Predictions","created":"2021-10-09","cited_by_count":22,"area":null},{"id":"2205.07704","title":"From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses","created":"2022-05-16","cited_by_count":22,"area":null},{"id":"2211.01568","title":"Fine-Tuning Language Models via Epistemic Neural Networks","created":"2022-11-03","cited_by_count":22,"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":"2202.13509","title":"Evaluating High-Order Predictive Distributions in Deep Learning","created":"2022-02-28","cited_by_count":10,"area":null},{"id":"2202.11474","title":"Residual Bootstrap Exploration for Stochastic Linear Bandit","created":"2022-02-23","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":"2502.07064","title":"Contextual Thompson Sampling via Generation of Missing Data","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2102.00966","title":"Risk Aware and Multi-Objective Decision Making with Distributional Monte Carlo Tree Search","created":"2021-02-01","cited_by_count":5,"area":null},{"id":"2102.03719","title":"State-Aware Variational Thompson Sampling for Deep Q-Networks","created":"2021-02-07","cited_by_count":5,"area":null},{"id":"2211.04009","title":"SOTIF Entropy: Online SOTIF Risk Quantification and Mitigation for Autonomous Driving","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2111.09724","title":"From Optimality to Robustness: Dirichlet Sampling Strategies in Stochastic Bandits","created":"2021-11-18","cited_by_count":4,"area":null},{"id":"2108.00236","title":"Debiasing Samples from Online Learning Using Bootstrap","created":"2021-07-31","cited_by_count":3,"area":null},{"id":"2203.01004","title":"Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise","created":"2022-03-02","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":"2305.10267","title":"State Representation Learning Using an Unbalanced Atlas","created":"2023-05-17","cited_by_count":3,"area":null},{"id":"2103.04387","title":"CORe: Capitalizing On Rewards in Bandit Exploration","created":"2021-03-07","cited_by_count":1,"area":null},{"id":"2211.06457","title":"The Implicit Delta Method","created":"2022-11-11","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":"2107.08383","title":"GuideBoot: Guided Bootstrap for Deep Contextual Bandits","created":"2021-07-18","cited_by_count":0,"area":null},{"id":"2109.08518","title":"Knowledge is reward: Learning optimal exploration by predictive reward cashing","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2205.02944","title":"A Deep Bayesian Bandits Approach for Anticancer Therapy: Exploration via Functional Prior","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2209.05278","title":"A Nonparametric Contextual Bandit with Arm-level Eligibility Control for Customer Service Routing","created":"2022-09-08","cited_by_count":0,"area":null},{"id":"2403.10671","title":"Variation Due to Regularization Tractably Recovers Bayesian Deep Learning","created":"2024-03-15","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":"2503.04518","title":"Leveraging priors on distribution functions for multi-arm bandits","created":"2025-03-06","cited_by_count":0,"area":null}],"next_cursor":null}