{"total":35,"rows":[{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"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":"2205.01970","title":"Non-Stationary Bandit Learning via Predictive Sampling","created":"2022-05-04","cited_by_count":21,"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":"2110.13973","title":"The Value of Information When Deciding What to Learn","created":"2021-10-26","cited_by_count":15,"area":null},{"id":"2102.06593","title":"Pareto Optimal Model Selection in Linear Bandits","created":"2021-02-12","cited_by_count":14,"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":"2302.04452","title":"An Information-Theoretic Analysis of Nonstationary Bandit Learning","created":"2023-02-09","cited_by_count":11,"area":null},{"id":"2101.01086","title":"Be Greedy in Multi-Armed Bandits","created":"2021-01-04","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":"2102.09488","title":"A Bit Better? Quantifying Information for Bandit Learning","created":"2021-02-18","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":"2209.07676","title":"Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning","created":"2022-09-16","cited_by_count":5,"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":"2308.08291","title":"Robust Bayesian Satisficing","created":"2023-08-16","cited_by_count":3,"area":null},{"id":"2308.15856","title":"Domain Generalization without Excess Empirical Risk","created":"2023-08-30","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":"2206.02025","title":"Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning","created":"2022-06-04","cited_by_count":2,"area":null},{"id":"2505.15342","title":"Policy Testing in Markov Decision Processes","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2408.15535","title":"Improving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2506.01625","title":"Robust Satisficing Gaussian Process Bandits Under Adversarial Attacks","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2605.19215","title":"Not all uncertainty is alike: volatility, stochasticity, and exploration","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2209.08197","title":"Thompson Sampling with Virtual Helping Agents","created":"2022-09-16","cited_by_count":0,"area":null},{"id":"2212.00615","title":"Online Learning-based Waveform Selection for Improved Vehicle Recognition in Automotive Radar","created":"2022-12-01","cited_by_count":0,"area":null},{"id":"2307.02379","title":"Machine learning at the mesoscale: a computation-dissipation bottleneck","created":"2023-07-05","cited_by_count":0,"area":null},{"id":"2407.12178","title":"Exploration Unbound","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2508.15966","title":"Vector preference-based contextual bandits under distributional shifts","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2512.20096","title":"Information-directed sampling for bandits: a primer","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2603.18514","title":"On the Peril of (Even a Little) Nonstationarity in Satisficing Regret Minimization","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2605.13287","title":"Delightful Exploration","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.31034","title":"Annealed Softmax Greedy in Many-Armed Bayesian Bandits","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.08369","title":"An Information-Theoretic Definition for Open-Ended Learning","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2610.12960","title":"DataCupid: Stable Matching Repair for Training Data Acquisition with Delayed Feedback","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}