Commit ·
6bf1b77
1
Parent(s): 61343e6
Update README.md
Browse files
README.md
CHANGED
|
@@ -36,21 +36,23 @@ model = load_from_hub(repo_id='Francesco-A/a2c-PandaReachDense-v3',
|
|
| 36 |
```
|
| 37 |
|
| 38 |
## Training details (last output)
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
|
| 45 |
-
|
|
| 46 |
-
|
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
|
|
|
|
|
|
|
|
| 36 |
```
|
| 37 |
|
| 38 |
## Training details (last output)
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
Metric | Value
|
| 42 |
+
---------------------|--------
|
| 43 |
+
rollout/ep_len_mean | 4.05
|
| 44 |
+
rollout/ep_rew_mean | -0.317
|
| 45 |
+
time/fps | 378
|
| 46 |
+
time/iterations | 50000
|
| 47 |
+
time/time_elapsed | 2641
|
| 48 |
+
time/total_timesteps | 1000000
|
| 49 |
+
train/entropy_loss | 1.25
|
| 50 |
+
train/explained_variance | 0.975
|
| 51 |
+
train/learning_rate | 0.0007
|
| 52 |
+
train/n_updates | 49999
|
| 53 |
+
train/policy_loss | -0.0935
|
| 54 |
+
train/std | 0.185
|
| 55 |
+
train/value_loss | 0.0306
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
|