ashkid commited on
Commit
e1a6ff2
·
verified ·
1 Parent(s): 1d6583a

Push agent to the Hub

Browse files
README.md CHANGED
@@ -17,7 +17,7 @@ model-index:
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
- value: 22.10 +/- 75.60
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -32,8 +32,8 @@ model-index:
32
  'seed': 1
33
  'torch_deterministic': True
34
  'cuda': True
35
- 'track': False
36
- 'wandb_project_name': 'cleanRL'
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
@@ -45,7 +45,7 @@ model-index:
45
  'gae': True
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
48
- 'num_minibatches': 4
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': 'ashkid/ppo-LunarLander-v2-unit8'
58
  'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 176.23 +/- 92.81
21
  name: mean_reward
22
  verified: false
23
  ---
 
32
  'seed': 1
33
  'torch_deterministic': True
34
  'cuda': True
35
+ 'track': True
36
+ 'wandb_project_name': 'ppo-LunarLander-v2-unit8'
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
 
45
  'gae': True
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
48
+ 'num_minibatches': 64
49
  'update_epochs': 4
50
  'norm_adv': True
51
  'clip_coef': 0.2
 
56
  'target_kl': None
57
  'repo_id': 'ashkid/ppo-LunarLander-v2-unit8'
58
  'batch_size': 512
59
+ 'minibatch_size': 8}
60
  ```
61
 
logs/events.out.tfevents.1740148839.autodl-container-efaf408b83-1c57e0aa.4439.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e3abc2c41cf6b29807321d2dcccbc693e4ce09865d80b9c48bc510e19b0a0c
3
+ size 747498
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82a5696963253e985fed3a121e7adcdfc3ed9e2b442fe06887c5a3213bae084a
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f34fe6a10e4d5b829e5d68b9ec1d5d7b3ae7b3016fdd1786cdf30246889f212d
3
  size 43026
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c69fdfbbbcac61803fb0cf01fd7a4c4e32ff21ce8f14305fad3af072ef7b7a5
3
- size 195256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db4f53d32f3bf67c8bc766151300931a62f403ee7c9d0d0cdfcd55720302a28d
3
+ size 195500
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "LunarLander-v2", "mean_reward": 22.09702101150861, "std_reward": 75.60035009160173, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-21T22:24:33.561534"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 176.23069170335305, "std_reward": 92.81125798593652, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-21T23:22:23.305105"}