Upload folder using huggingface_hub
Browse files- README.md +28 -9
- hyperparameters.json +1 -0
- results.json +1 -1
README.md
CHANGED
@@ -1,10 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- Hopper-v5
|
4 |
+
- reinforcement-learning
|
5 |
+
- decision-transformer
|
6 |
+
- deep-reinforcement-learning
|
7 |
+
- custom-implementation
|
8 |
+
library_name: transformers
|
9 |
+
---
|
10 |
|
11 |
+
# Decision Transformer for Hopper-v5
|
12 |
+
|
13 |
+
This is a trained Decision Transformer model for the Hopper-v5 environment.
|
14 |
+
|
15 |
+
## Model Details
|
16 |
+
- Environment: Hopper-v5
|
17 |
+
- Model: Decision Transformer
|
18 |
+
- Training framework: PyTorch
|
19 |
+
|
20 |
+
## Hyperparameters
|
21 |
+
{
|
22 |
+
"max_ep_len": 1000,
|
23 |
+
"state_dim": 11,
|
24 |
+
"act_dim": 3,
|
25 |
+
"target_return": 3.6
|
26 |
+
}
|
27 |
+
|
28 |
+
## Video Preview
|
29 |
+
The model demonstrates the hopping behavior learned through Decision Transformer training.
|
hyperparameters.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"env_id": "Hopper-v5", "max_ep_len": 1000, "state_dim": 11, "act_dim": 3, "target_return": 3.6, "state_mean": [1.3490015, -0.11208222, -0.5506444, -0.13188992, -0.00378754, 2.6071432, 0.02322114, -0.01626922, -0.06840388, -0.05183131, 0.04272673], "state_std": [0.15980862, 0.0446214, 0.14307782, 0.17629202, 0.5912333, 0.5899924, 1.5405099, 0.8152689, 2.0173461, 2.4107876, 5.8440027]}
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"env_id": "Hopper-v5", "eval_datetime": "2025-01-20T19:
|
|
|
1 |
+
{"env_id": "Hopper-v5", "eval_datetime": "2025-01-20T19:47:24.817410"}
|