Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations.

Sangwon Seo Vaibhav V. Unhelkar

Published in: CoRR (2022)

Keyphrases

imitation learning
semi supervised
reinforcement learning
robotic systems
maximum margin
semi supervised learning
humanoid robot
labeled data
unlabeled data
optimal policy
active learning
supervised learning
pairwise
support vector machine
reinforcement learning methods
relational domains
computer vision