Learning Task-Agnostic Action Spaces for Movement Optimization

Amin Babadi
Amin Babadi
Michiel van de Panne
Michiel van de Panne
Cited by: 0|Bibtex|Views41
Other Links: arxiv.org

Abstract:

We propose a novel method for exploring the dynamics of physically based animated characters, and learning a task-agnostic action space that makes movement optimization easier. Like several previous papers, we parameterize actions as target states, and learn a short-horizon goal-conditioned low-level control policy that drives the agent...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments