{"total":21,"rows":[{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45,"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":"2210.16877","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","created":"2022-10-30","cited_by_count":6,"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":"2308.15856","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":"2404.19292","title":"Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2505.02949","title":"Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2207.02365","title":"Linear Jamming Bandits: Sample-Efficient Learning for Non-Coherent Digital Jamming","created":"2022-07-05","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":"2406.14476","title":"Learning telic-controllable state representations","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2407.12178","title":"Exploration Unbound","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2510.08113","title":"Bayesian Decision Making around Experts","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2606.06123","title":"Adaptive state-action abstractions via rate-distortion","created":"2026-06-04","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}],"next_cursor":null}