Learning Agile Locomotion Skills with a Mentor

George Yu
George Yu
Alejandro Escontrela
Alejandro Escontrela
Deepali Jain
Deepali Jain
Cited by: 0|Bibtex|Views0
Other Links: arxiv.org

Abstract:

Developing agile behaviors for legged robots remains a challenging problem. While deep reinforcement learning is a promising approach, learning truly agile behaviors typically requires tedious reward shaping and careful curriculum design. We formulate agile locomotion as a multi-stage learning problem in which a mentor guides the agent ...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments