Unsupervised Perceptual Rewards for Imitation Learning.

Pierre Sermanet Kelvin Xu Sergey Levine

Published in: CoRR (2016)

Keyphrases

imitation learning
reinforcement learning
unsupervised learning
robotic systems
supervised learning
maximum margin
markov decision processes
humanoid robot
state space
semi supervised
function approximation
learning algorithm
reinforcement learning methods
vision system
text classification
control problems