2 papers
cs.RO2025
Humanoid Whole-Body Badminton via an Annealed Reinforcement Learning Curriculum
Chenhao Liu, Leyun Jiang, Yibo Wang +4
Humanoid robots have demonstrated strong capabilities for interacting with static scenes across locomotion and manipulation, yet dynamic real-world interactions remain challenging.…
cs.LG2024
Learning Off-policy with Model-based Intrinsic Motivation For Active Online Exploration
Yibo Wang, Jiang Zhao
Recent advancements in deep reinforcement learning (RL) have demonstrated notable progress in sample efficiency, spanning both model-based and model-free paradigms. Despite the ide…