{"total":13,"rows":[{"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":"2112.05244","title":"An Experimental Design Perspective on Model-Based Reinforcement Learning","created":"2021-12-09","cited_by_count":16,"area":null},{"id":"2205.10895","title":"Contextual Information-Directed Sampling","created":"2022-05-22","cited_by_count":16,"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":"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":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2407.12178","title":"Exploration Unbound","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2507.00851","title":"Aligning Learning and Endogenous Decision-Making","created":"2025-07-01","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":"2610.00424","title":"Target-Dependent Limits of Causal Repair: A Leading-Log Frontier in a Gaussian Model","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}