← Back to Benchmarks
simmediummanipulation-datametric · varies
ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning
Description
Long-horizon manipulation has been a long-standing challenge in the robotics community. We propose ReinforceGen, a system that combines task decomposition, data generation, imitation learning, and motion planning to form an initial solution, and improves each component through reinforcement-learning-based fine-tuning. ReinforceGen first segments the task into multiple localized skills, which are connected through motion planning. The skills and motion planning targets are trained with imitation