jaymanvirk
commited on
Commit
•
79ffbb7
1
Parent(s):
a5fd3a5
set hyperparameters as json in model card
Browse files- README.md +2 -28
- 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 |
---
|
@@ -28,31 +28,5 @@ model-index:
|
|
28 |
|
29 |
# Hyperparameters
|
30 |
|
31 |
-
{'seed': 0
|
32 |
-
'torch_deterministic': True
|
33 |
-
'cuda': True
|
34 |
-
'track': False
|
35 |
-
'wandb_project_name': 'cleanRL'
|
36 |
-
'wandb_entity': None
|
37 |
-
'capture_video': False
|
38 |
-
'env_id': 'LunarLander-v2'
|
39 |
-
'total_timesteps': 100000
|
40 |
-
'learning_rate': 0.001
|
41 |
-
'num_envs': 8
|
42 |
-
'num_steps': 256
|
43 |
-
'anneal_lr': True
|
44 |
-
'gae': True
|
45 |
-
'gamma': 0.99
|
46 |
-
'gae_lambda': 0.95
|
47 |
-
'num_minibatches': 4
|
48 |
-
'update_epochs': 4
|
49 |
-
'norm_adv': True
|
50 |
-
'clip_coef': 0.2
|
51 |
-
'clip_vloss': True
|
52 |
-
'ent_coef': 0.01
|
53 |
-
'vf_coef': 0.5
|
54 |
-
'max_grad_norm': 0.5
|
55 |
-
'target_kl': None
|
56 |
-
'batch_size': 2048
|
57 |
-
'minibatch_size': 512}
|
58 |
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -58.74 +/- 80.66
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
28 |
|
29 |
# Hyperparameters
|
30 |
|
31 |
+
{'seed': 0, 'torch_deterministic': True, 'cuda': True, 'track': False, 'wandb_project_name': 'cleanRL', 'wandb_entity': None, 'capture_video': False, 'env_id': 'LunarLander-v2', 'total_timesteps': 100000, 'learning_rate': 0.001, 'num_envs': 8, 'num_steps': 256, 'anneal_lr': True, 'gae': True, 'gamma': 0.99, 'gae_lambda': 0.95, 'num_minibatches': 4, 'update_epochs': 4, 'norm_adv': True, 'clip_coef': 0.2, 'clip_vloss': True, 'ent_coef': 0.01, 'vf_coef': 0.5, 'max_grad_norm': 0.5, 'target_kl': None, 'batch_size': 2048, 'minibatch_size': 512}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
|
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": -58.74375789537991, "std_reward": 80.66261767815269, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-16T07:18:40.540856"}
|