Deep Adversarial Reinforcement Learning for Object Disentangling.

Melvin Laux Oleg Arenz Jan Peters Joni Pajarinen

Published in: IROS (2020)

Keyphrases

reinforcement learning
d objects
function approximation
object model
multi agent
model free
machine learning
viewpoint
complex objects
object segmentation
action space
temporal difference
complex scenes
multiple objects
spatial relations
object tracking
pose estimation
active learning
learning algorithm