I am interested in imitation learning. As far as I know, “policy for bin picking” is trained with the same gqcnn as Dexnet2.0/Dexnet3.0.
The main problem confused me is the demonstration is a sequence of training data， I don‘t know how to use these data sequences to train gqcnn to classify actions. Is there any detail explanation?
I am interested in imitation learning. As far as I know, “policy for bin picking” is trained with the same gqcnn as Dexnet2.0/Dexnet3.0. The main problem confused me is the demonstration is a sequence of training data， I don‘t know how to use these data sequences to train gqcnn to classify actions. Is there any detail explanation?