Reparameterized Variational Divergence Minimization for Stable Imitation

Dilip Arumugam
Dilip Arumugam
Elnaz Nouri
Elnaz Nouri
Cited by: 0|Bibtex|Views63
Other Links: arxiv.org

Abstract:

While recent state-of-the-art results for adversarial imitation-learning algorithms are encouraging, recent works exploring the imitation learning from observation (ILO) setting, where trajectories \textit{only} contain expert observations, have not been met with the same success. Inspired by recent investigations of $f$-divergence mani...More

Code:

Data:

Your rating :
0

 

Tags
Comments