Conference item
Neural probabilistic motor primitives for humanoid control
- Abstract:
-
We focus on the problem of learning a single motor module that can flexibly express a range of behaviors for the control of high-dimensional physically simulated humanoids. To do this, we propose a motor architecture that has the general structure of an inverse model with a latent-variable bottleneck. We show that it is possible to train this model entirely offline to compress thousands of expert policies and learn a motor primitive embedding space. The trained neural probabilistic motor prim...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Bibliographic Details
- Journal:
- International Conference on Learning Representations Journal website
- Host title:
- International Conference on Learning Representations
- Publication date:
- 2019-05-06
- Acceptance date:
- 2018-12-21
- Event location:
- New Orleans, USA
- Source identifiers:
-
949226
Item Description
- Pubs id:
-
pubs:949226
- UUID:
-
uuid:6a02be08-a2b6-46b5-a5cf-0ee99a23c67a
- Local pid:
- pubs:949226
- Deposit date:
- 2019-02-06
Terms of use
- Copyright holder:
- Merel et al
- Copyright date:
- 2019
- Notes:
- This paper has been presented at the Seventh International Conference on Learning Representations, 06-09 May 2019, New Orleans, USA.
If you are the owner of this record, you can report an update to it here: Report update to this record