Reinforcement Learning
Transformers
Safetensors
alpha_pilot_dqn
gymnasium
dqn
lunar-lander
alpha-pilot
custom_code
Instructions to use prostochel097/alphapilot-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prostochel097/alphapilot-v1 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("prostochel097/alphapilot-v1", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Create configuration_alphapilot.py
Browse files- configuration_alphapilot.py +18 -0
configuration_alphapilot.py
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers import PretrainedConfig
|
| 2 |
+
|
| 3 |
+
class AlphaPilotConfig(PretrainedConfig):
|
| 4 |
+
model_type = "alpha_pilot_dqn"
|
| 5 |
+
|
| 6 |
+
def __init__(
|
| 7 |
+
self,
|
| 8 |
+
state_dim=8,
|
| 9 |
+
action_dim=4,
|
| 10 |
+
hidden_layers=[256, 128],
|
| 11 |
+
activation="ReLU",
|
| 12 |
+
**kwargs
|
| 13 |
+
):
|
| 14 |
+
self.state_dim = state_dim
|
| 15 |
+
self.action_dim = action_dim
|
| 16 |
+
self.hidden_layers = hidden_layers
|
| 17 |
+
self.activation = activation
|
| 18 |
+
super().__init__(**kwargs)
|