{"total":9,"rows":[{"id":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2602.08040","title":"FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff","created":"2026-02-08","cited_by_count":7,"area":null},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2609.16683","title":"Weave: Learning Whole-Body Dexterous Loco-Manipulation from Human-Object Interactions","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2506.01568","title":"Trajectory First: A Curriculum for Discovering Diverse Policies","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2602.21680","title":"Hierarchical Lead Critic based Multi-Agent Reinforcement Learning","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2610.10857","title":"Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.13354","title":"AlphaNIST: Emergent Assembly Skills from Binary Task Rewards","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}