Upload model from pretrained_model
Browse files
README.md
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: lerobot
|
| 3 |
+
tags:
|
| 4 |
+
- act
|
| 5 |
+
- pusht
|
| 6 |
+
- reinforcement-learning
|
| 7 |
+
- robot
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# ACT Policy for pusht
|
| 11 |
+
|
| 12 |
+
This model was trained using [LeRobot](https://github.com/huggingface/lerobot).
|
| 13 |
+
|
| 14 |
+
## Model Details
|
| 15 |
+
- **Repository**: [vvrs/act-pusht](https://huggingface.co/vvrs/act-pusht)
|
| 16 |
+
- **Policy Type**: act
|
| 17 |
+
- **Environment**: pusht
|
| 18 |
+
|
| 19 |
+
## Hyperparameters
|
| 20 |
+
- **n_action_steps**: 10
|
| 21 |
+
- **chunk_size**: 50
|
| 22 |
+
- **dim_model**: 512
|
| 23 |
+
- **n_encoder_layers**: 4
|
| 24 |
+
- **dropout**: 0.1
|
| 25 |
+
- **kl_weight**: 0.26090695687163257
|
| 26 |
+
- **optimizer_lr**: 7.765556097859912e-05
|
| 27 |
+
|
| 28 |
+
## Usage
|
| 29 |
+
|
| 30 |
+
```python
|
| 31 |
+
from lerobot.common.policies.act.modeling_act import ACTPolicy
|
| 32 |
+
from lerobot.common.policies.act.configuration_act import ACTConfig
|
| 33 |
+
|
| 34 |
+
# Load the policy from the Hub
|
| 35 |
+
policy = ACTPolicy.from_pretrained("vvrs/act-pusht")
|
| 36 |
+
|
| 37 |
+
# Use the policy for inference...
|
| 38 |
+
```
|