Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video
Oier Mees,Markus Merklinger,Gabriel Kalweit,Wolfram Burgard,Oier Mees,Markus Merklinger,Gabriel Kalweit,Wolfram Burgard
Key challenges for the deployment of reinforcement learning (RL) agents in the real world are the discovery, representation and reuse of skills in the absence of a reward function. To this end, we propose a novel approach to learn a task-agnostic skill embedding space from unlabeled multi-view videos. Our method learns a general skill embedding independently from the task context by using an adver...
