{"total":8,"rows":[{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2312.12275","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","created":"2023-12-19","cited_by_count":27,"area":null},{"id":"2409.04180","title":"The Prevalence of Neural Collapse in Neural Multivariate Regression","created":"2024-09-06","cited_by_count":21,"area":null},{"id":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2602.09580","title":"SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2403.15502","title":"Sequential Decision-Making for Inline Text Autocomplete","created":"2024-03-21","cited_by_count":2,"area":null},{"id":"2411.04138","title":"NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2505.09308","title":"Neural Multivariate Regression: Qualitative Insights from the Unconstrained Feature Model","created":"2025-05-14","cited_by_count":2,"area":null}],"next_cursor":null}