Upload configuration.yaml with huggingface_hub
Browse files- configuration.yaml +23 -1
configuration.yaml
CHANGED
|
@@ -1,2 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
env_id: ML-Agents-Pyramids
|
| 2 |
-
mean_reward: 1.85
|
|
|
|
| 1 |
+
default_settings: null
|
| 2 |
+
behaviors:
|
| 3 |
+
Pyramids:
|
| 4 |
+
trainer_type: ppo
|
| 5 |
+
hyperparameters:
|
| 6 |
+
batch_size: 128
|
| 7 |
+
buffer_size: 2048
|
| 8 |
+
learning_rate: 0.0003
|
| 9 |
+
beta: 0.005
|
| 10 |
+
epsilon: 0.2
|
| 11 |
+
lambd: 0.95
|
| 12 |
+
num_epoch: 3
|
| 13 |
+
network_settings:
|
| 14 |
+
normalize: false
|
| 15 |
+
hidden_units: 128
|
| 16 |
+
num_layers: 2
|
| 17 |
+
reward_signals:
|
| 18 |
+
extrinsic:
|
| 19 |
+
gamma: 0.99
|
| 20 |
+
strength: 1.0
|
| 21 |
+
max_steps: 500000
|
| 22 |
+
time_horizon: 64
|
| 23 |
+
summary_freq: 10000
|
| 24 |
env_id: ML-Agents-Pyramids
|
|
|