Push agent to the Hub
Browse files- README.md +6 -6
- logs/events.out.tfevents.1718025239.887b5cfc0142.11575.0 +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 |
---
|
|
@@ -38,15 +38,15 @@ model-index:
|
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
'total_timesteps': 50000
|
| 41 |
-
'learning_rate':
|
| 42 |
'num_envs': 4
|
| 43 |
-
'num_steps':
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.99
|
| 47 |
'gae_lambda': 0.95
|
| 48 |
'num_minibatches': 8
|
| 49 |
-
'update_epochs':
|
| 50 |
'norm_adv': True
|
| 51 |
'clip_coef': 0.2
|
| 52 |
'clip_vloss': True
|
|
@@ -55,7 +55,7 @@ model-index:
|
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'arhamk/ppo-LunarLander-v2-2'
|
| 58 |
-
'batch_size':
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -198.93 +/- 138.92
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
'total_timesteps': 50000
|
| 41 |
+
'learning_rate': 1e-05
|
| 42 |
'num_envs': 4
|
| 43 |
+
'num_steps': 2048
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.99
|
| 47 |
'gae_lambda': 0.95
|
| 48 |
'num_minibatches': 8
|
| 49 |
+
'update_epochs': 10
|
| 50 |
'norm_adv': True
|
| 51 |
'clip_coef': 0.2
|
| 52 |
'clip_vloss': True
|
|
|
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'arhamk/ppo-LunarLander-v2-2'
|
| 58 |
+
'batch_size': 8192
|
| 59 |
+
'minibatch_size': 1024}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1718025239.887b5cfc0142.11575.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6080a4216017af3fe831b9c3b11759a46b1153aaf3fab6762c2d9be3087b442e
|
| 3 |
+
size 68568
|
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:fbdda57fcf2dccebfd2e45a58ccf4fcfd5c9b9049649eb63e9b4aeaac316fa57
|
| 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": -198.92899401262682, "std_reward": 138.91576028315262, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:14:39.301212"}
|