{"total":9,"rows":[{"id":"2508.08189","title":"Reinforcement Learning for Large Model: A Survey","created":"2025-08-11","cited_by_count":9,"area":"deeprl"},{"id":"2510.04786","title":"Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning","created":"2025-10-06","cited_by_count":9,"area":"deeprl"},{"id":"2512.05591","title":"Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning","created":"2025-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2605.04920","title":"Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization","created":"2026-05-06","cited_by_count":2,"area":"deeprl"},{"id":"2606.06096","title":"OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation","created":"2026-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2510.25311","title":"Dense and Diverse Goal Coverage in Multi Goal Reinforcement Learning","created":"2025-10-29","cited_by_count":0,"area":"deeprl"},{"id":"2512.10365","title":"GPG: Generalized Policy Gradient Theorem for Transformer-based Policies","created":"2025-12-11","cited_by_count":0,"area":"deeprl"},{"id":"2608.18881","title":"Falcon Perception-HD: High Density Perception via Reinforcement Learning","created":"2026-08-19","cited_by_count":0,"area":"deeprl"},{"id":"2610.02846","title":"Understanding Enrichment in Reinforcement Learning","created":"2026-10-02","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}