ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning

作者：Preprint. Under review. Zihan Zhou, Animesh Garg, Ajay Mandlekar, Caelan Garrett · 单位：University of Toronto, Vector Institute Georgia Institute of Technology NVIDIA Research · 会议/期刊：arXiv · 日期：2025-12-18 · 来源：Low-Level Learning-Based Action Modelling / Learning Strategy / RL and IL / IL Pre-training + RL Fine-tuning