{"total":15,"rows":[{"id":"2510.14830","title":"RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning","created":"2025-10-16","cited_by_count":59,"area":"deeprl"},{"id":"2408.10215","title":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications","created":"2024-07-22","cited_by_count":38,"area":"deeprl"},{"id":"2404.14735","title":"Rank2Reward: Learning Shaped Reward Functions from Passive Video","created":"2024-04-23","cited_by_count":32,"area":"deeprl"},{"id":"2403.17320","title":"Leveraging Symmetry in RL-based Legged Locomotion Control","created":"2024-03-26","cited_by_count":25,"area":"deeprl"},{"id":"2405.03379","title":"Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning","created":"2024-05-06","cited_by_count":13,"area":"deeprl"},{"id":"2410.19989","title":"On-Robot Reinforcement Learning with Goal-Contrastive Rewards","created":"2024-10-25","cited_by_count":8,"area":"deeprl"},{"id":"2410.21795","title":"Robot Policy Learning with Temporal Optimal Transport Reward","created":"2024-10-29","cited_by_count":8,"area":"deeprl"},{"id":"2403.07916","title":"Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization","created":"2024-02-27","cited_by_count":4,"area":"deeprl"},{"id":"2509.13949","title":"SHaRe-RL: Structured, Interactive Reinforcement Learning for Contact-Rich Industrial Assembly Tasks","created":"2025-09-17","cited_by_count":3,"area":"deeprl"},{"id":"2508.01247","title":"Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policy","created":"2025-08-02","cited_by_count":2,"area":"deeprl"},{"id":"2602.12636","title":"Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL","created":"2026-02-13","cited_by_count":2,"area":"deeprl"},{"id":"2407.03311","title":"Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples","created":"2024-07-03","cited_by_count":1,"area":"deeprl"},{"id":"2601.22449","title":"Emergence of Physical Intelligence via Controllable Information Production","created":"2026-01-30","cited_by_count":1,"area":"deeprl"},{"id":"2604.15757","title":"Multi-objective Reinforcement Learning With Augmented States Requires Rewards After Deployment","created":"2026-04-17","cited_by_count":0,"area":"deeprl"},{"id":"2609.19962","title":"Hybrid Residual Reinforcement Learning for Contact-Rich Robotic Book Insertion","created":"2026-09-17","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}