AI RESEARCH
HoRD: Robust Humanoid Control via History-Conditioned Reinforcement Learning and Online Distillation
arXiv CS.LG
•
ArXi:2602.04412v3 Announce Type: replace-cross Humanoid robots can suffer significant performance drops under small changes in dynamics, task specifications, or environment setup. We propose HoRD, a two-stage learning framework for robust humanoid control under domain shift. First, we train a high-performance teacher policy via history-conditioned reinforcement learning, where the policy infers latent dynamics context from recent state--action trajectories to adapt online to diverse randomized dynamics.