Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -24,7 +24,7 @@ This is a **task policy, not a pretrained base**. For post-training on your own
|
|
| 24 |
|
| 25 |
Policy for the NeoSim `insert_USB` task.
|
| 26 |
|
| 27 |
-
**
|
| 28 |
|
| 29 |
### Serving
|
| 30 |
|
|
@@ -38,14 +38,13 @@ python scripts/serve_zmq.py --config sim_single_arm_tactile \
|
|
| 38 |
|
| 39 |
## Evaluation protocol
|
| 40 |
|
| 41 |
-
|
| 42 |
-
(branch `NeoSim` of [anlorla/UniVTAC](https://github.com/anlorla/UniVTAC))
|
| 43 |
-
three tasks were tightened after these numbers were
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
identical evaluation on a fixed checkpoint has produced 60 / 30 / 50 on the same task.
|
| 49 |
|
| 50 |
## Caveat on the tactile pathway
|
| 51 |
|
|
|
|
| 24 |
|
| 25 |
Policy for the NeoSim `insert_USB` task.
|
| 26 |
|
| 27 |
+
**80%**, first attempt.
|
| 28 |
|
| 29 |
### Serving
|
| 30 |
|
|
|
|
| 38 |
|
| 39 |
## Evaluation protocol
|
| 40 |
|
| 41 |
+
Measured on the UniVTAC simulator at commit `695a22d`
|
| 42 |
+
(branch `NeoSim` of [anlorla/UniVTAC](https://github.com/anlorla/UniVTAC)), on held-out seeds
|
| 43 |
+
starting at 100. Success criteria on three tasks were tightened after these numbers were
|
| 44 |
+
measured, so a success rate on this benchmark is not comparable without the simulator commit
|
| 45 |
+
beside it; see
|
| 46 |
+
[docs/EVAL.md](https://github.com/neoteai/N0-VTLA/blob/main/docs/EVAL.md) for the details and for
|
| 47 |
+
the full evaluation procedure.
|
|
|
|
| 48 |
|
| 49 |
## Caveat on the tactile pathway
|
| 50 |
|