robotics-self-play.github.io

Robotics Asymmetric Self-Play | We use asymmetric self-play to train a goal-conditioned policy for complex object manipulation tasks, and the learned policy can zero-shot generalize to many manually d…

We use asymmetric self-play to train a goal-conditioned policy for complex object manipulation tasks, and the learned policy can zero-shot generalize to many manually designed holdout tasks.