Unsupervised Reinforcement Learning

I-BFM: Reward-Conditioned Robust Humanoid Interaction via Unsupervised Reinforcement Learning
I-BFM: Reward-Conditioned Robust Humanoid Interaction via Unsupervised Reinforcement Learning

A shared reward-conditioned policy learns humanoid-object interaction and recovery through unsupervised reinforcement learning.

Oct 5, 2026