Metadata for robotics policy model for Asimov 🔥 (#1)
Browse files- Metadata for robotics policy model for Asimov 🔥 (666fa2785f21ea73fca0a93c4c3d9f353be983de)
Co-authored-by: Julien Chaumond <julien-c@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: bsd-3-clause
|
| 3 |
---
|
| 4 |
|
|
@@ -8,4 +10,4 @@ license: bsd-3-clause
|
|
| 8 |
- `policy.onnx` is the exported policy for inference, producing joint-position actions.
|
| 9 |
- `agent.yaml` records the actor-critic and AMP training settings, including the motion data configuration.
|
| 10 |
- `env.yaml` records the simulation and locomotion task settings, including observations, actions, commands, and rewards.
|
| 11 |
-
- Training and evaluation code: [menloresearch/isaac_asimov](https://github.com/menloresearch/isaac_asimov).
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: asimov
|
| 3 |
+
pipeline_tag: robotics
|
| 4 |
license: bsd-3-clause
|
| 5 |
---
|
| 6 |
|
|
|
|
| 10 |
- `policy.onnx` is the exported policy for inference, producing joint-position actions.
|
| 11 |
- `agent.yaml` records the actor-critic and AMP training settings, including the motion data configuration.
|
| 12 |
- `env.yaml` records the simulation and locomotion task settings, including observations, actions, commands, and rewards.
|
| 13 |
+
- Training and evaluation code: [menloresearch/isaac_asimov](https://github.com/menloresearch/isaac_asimov).
|