Scaling Simulation-to-Real Transfer by Learning Composable Robot Skills

Ryan Julian
Ryan Julian
Eric Heiden
Eric Heiden
Zhanpeng He
Zhanpeng He
Hejia Zhang
Hejia Zhang

ISER, pp. 267-279, 2018.

Cited by: 0|Bibtex|Views23|Links
EI

Abstract:

We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation-reality gap, we learn a set of diverse policies that are parameterized in a way that makes them easily reusable. This diversity and parameterization of...More

Code:

Data:

Your rating :
0

 

Tags
Comments