Login / Signup
Video Imitation GAN: Learning control policies by imitating raw videos using generative adversarial reward estimation.
Subhajit Chaudhury
Daiki Kimura
Tu-Hoa Pham
Asim Munawar
Ryuki Tachibana
Published in:
CoRR (2018)
Keyphrases
</>
reinforcement learning
video sequences
video frames
control policies
video data
video content
learning algorithm
real time
machine learning
parameter estimation
multiple agents
inverse reinforcement learning