Push agent to the Hub
Browse files- README.md +3 -3
- logs/events.out.tfevents.1718026936.887b5cfc0142.18868.0 +3 -0
- model.pt +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
|
@@ -17,7 +17,7 @@ model-index:
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
-
value: -
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
@@ -45,7 +45,7 @@ model-index:
|
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.98
|
| 47 |
'gae_lambda': 0.95
|
| 48 |
-
'num_minibatches':
|
| 49 |
'update_epochs': 4
|
| 50 |
'norm_adv': True
|
| 51 |
'clip_coef': 0.2
|
|
@@ -56,6 +56,6 @@ model-index:
|
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'arhamk/ppo-LunarLander-v2-2'
|
| 58 |
'batch_size': 8192
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -129.42 +/- 88.71
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.98
|
| 47 |
'gae_lambda': 0.95
|
| 48 |
+
'num_minibatches': 4
|
| 49 |
'update_epochs': 4
|
| 50 |
'norm_adv': True
|
| 51 |
'clip_coef': 0.2
|
|
|
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'arhamk/ppo-LunarLander-v2-2'
|
| 58 |
'batch_size': 8192
|
| 59 |
+
'minibatch_size': 2048}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1718026936.887b5cfc0142.18868.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82fa19eb67cc4045557c7f12d322279b088dace47fca686db47f458d5d8b3b9b
|
| 3 |
+
size 59181
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43026
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13fde366c21ba857b4d72d3585861c9117291e86520d76f8f06c228af447d672
|
| 3 |
size 43026
|
replay.mp4
CHANGED
|
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"env_id": "LunarLander-v2", "mean_reward": -
|
|
|
|
| 1 |
+
{"env_id": "LunarLander-v2", "mean_reward": -129.42277426291815, "std_reward": 88.71460396225297, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:42:38.051330"}
|