Update README.md
Browse files
README.md
CHANGED
@@ -8,14 +8,14 @@ pipeline_tag: robotics
|
|
8 |
|
9 |
VQ-BeT (as per [Behavior Generation with Latent Actions](https://arxiv.org/abs/2403.03181)) trained for the `PushT` environment from [gym-pusht](https://github.com/huggingface/gym-pusht).
|
10 |
|
11 |
-
![demo](demo.gif)
|
12 |
-
|
13 |
## How to Get Started with the Model
|
14 |
|
15 |
See the [LeRobot library](https://github.com/huggingface/lerobot) (particularly the [evaluation script](https://github.com/huggingface/lerobot/blob/main/lerobot/scripts/eval.py)) for instructions on how to load and evaluate this model.
|
16 |
|
17 |
## Training Details
|
18 |
|
|
|
|
|
19 |
The model was trained using this command:
|
20 |
|
21 |
```bash
|
@@ -40,7 +40,9 @@ The model was evaluated on the `PushT` environment from [gym-pusht](https://gith
|
|
40 |
- Maximum overlap with target (seen as `eval/avg_max_reward` in the charts above). This ranges in [0, 1].
|
41 |
- Success: whether or not the maximum overlap is at least 95%.
|
42 |
|
|
|
|
|
43 |
<blank>|Ours
|
44 |
-|-
|
45 |
-
Average max. overlap ratio | 0.887
|
46 |
Success rate for 500 episodes (%) | 66.0
|
|
|
8 |
|
9 |
VQ-BeT (as per [Behavior Generation with Latent Actions](https://arxiv.org/abs/2403.03181)) trained for the `PushT` environment from [gym-pusht](https://github.com/huggingface/gym-pusht).
|
10 |
|
|
|
|
|
11 |
## How to Get Started with the Model
|
12 |
|
13 |
See the [LeRobot library](https://github.com/huggingface/lerobot) (particularly the [evaluation script](https://github.com/huggingface/lerobot/blob/main/lerobot/scripts/eval.py)) for instructions on how to load and evaluate this model.
|
14 |
|
15 |
## Training Details
|
16 |
|
17 |
+
Trained with [LeRobot@342f429](https://github.com/huggingface/lerobot/tree/342f429f1c321a2b4501c3007b1dacba7244b469).
|
18 |
+
|
19 |
The model was trained using this command:
|
20 |
|
21 |
```bash
|
|
|
40 |
- Maximum overlap with target (seen as `eval/avg_max_reward` in the charts above). This ranges in [0, 1].
|
41 |
- Success: whether or not the maximum overlap is at least 95%.
|
42 |
|
43 |
+
The results of each of the individual rollouts may be found in [eval_info.json](eval_info.json).
|
44 |
+
|
45 |
<blank>|Ours
|
46 |
-|-
|
47 |
+
Average max. overlap ratio for 500 episodes | 0.887
|
48 |
Success rate for 500 episodes (%) | 66.0
|