Combating False Negatives in Adversarial Imitation Learning

Saharia Chitwan
Saharia Chitwan
Boussioux Leonard
Boussioux Leonard
Hui David Yu-Tung
Hui David Yu-Tung
Chevalier-Boisvert Maxime
Chevalier-Boisvert Maxime
Cited by: 0|Bibtex|Views70
Other Links: arxiv.org

Abstract:

In adversarial imitation learning, a discriminator is trained to differentiate agent episodes from expert demonstrations representing the desired behavior. However, as the trained policy learns to be more successful, the negative examples (the ones produced by the agent) become increasingly similar to expert ones. Despite the fact that ...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments