{"total":15,"rows":[{"id":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24,"area":null},{"id":"2503.03707","title":"Curating Demonstrations using Online Experience","created":"2025-03-05","cited_by_count":18,"area":null},{"id":"2310.01737","title":"Blending Imitation and Reinforcement Learning for Robust Policy Improvement","created":"2023-10-03","cited_by_count":17,"area":null},{"id":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2310.08549","title":"Cross-Episodic Curriculum for Transformer Agents","created":"2023-10-12","cited_by_count":10,"area":null},{"id":"2405.03735","title":"Select to Perfect: Imitating desired behavior from large multi-agent data","created":"2024-05-06","cited_by_count":4,"area":null},{"id":"2310.11531","title":"Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2312.04030","title":"Modeling Boundedly Rational Agents with Latent Inference Budgets","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2410.12217","title":"Accurate and Data-Efficient Toxicity Prediction when Annotators Disagree","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2402.06501","title":"Scalable Interactive Machine Learning for Future Command and Control","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2312.12102","title":"I-CEE: Tailoring Explanations of Image Classification Models to User Expertise","created":"2023-12-19","cited_by_count":1,"area":null},{"id":"2604.17289","title":"REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2404.17725","title":"Boltzmann State-Dependent Rationality","created":"2024-04-26","cited_by_count":0,"area":null},{"id":"2405.17047","title":"Interpretable Robotic Manipulation from Language","created":"2024-05-27","cited_by_count":0,"area":null},{"id":"2609.09250","title":"No Free Checker: A Survey of Verifiers for Robot Policies","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}