End-to-End Differentiable Adversarial Imitation Learning.

Nir Baram Oron Anschel Itai Caspi Shie Mannor

Published in: ICML (2017)

Keyphrases

end to end
imitation learning
reinforcement learning
humanoid robot
robotic systems
maximum margin
multi agent
congestion control
admission control
real time
reinforcement learning methods
data sets
machine learning
learning algorithm
logic programs