作者位次 #2/4IROS 2026Poster· Scaling Up Robot Policy Learning
Compositional Average Velocity Modeling for Efficient Diffusion Offline Reinforcement Learning
Thanh Nguyen · Abu Hanif Muhammad Syarubany · Hwanhee Kim · Chang D. Yoo
强化学习与后训练效率与系统长上下文与架构Reinforcement LearningLearning from ExperienceMachine Learning for Robot ControlOpenReview