Offline Learning from Demonstrations and Unlabeled Experience

Cited by: 0|Bibtex|Views19|Links

Abstract:

Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations. However, BC does not effectively leverage what we will refer to as unlabeled experience: data of mixed and unknown quality without reward annotations. This unlabel...More

Code:

Data:

Your rating :
0

 

Tags
Comments