rasyadanfz commited on
Commit
75765c2
·
verified ·
1 Parent(s): c37c7e8

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: -30.92 +/- 28.71
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,15 +37,15 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'learning_rate': 0.0002
41
  'total_timesteps': 750000
42
- 'num_envs': 8
43
- 'num_steps': 192
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.985
47
- 'gae_lambda': 0.96
48
- 'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
51
  'clip_coef': 0.2
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'rasyadanfz/LunarLander-v2-scratch'
58
- 'batch_size': 1536
59
- 'minibatch_size': 384}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 3.47 +/- 113.02
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'learning_rate': 0.0008
41
  'total_timesteps': 750000
42
+ 'num_envs': 16
43
+ 'num_steps': 160
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.97
47
+ 'gae_lambda': 0.94
48
+ 'num_minibatches': 8
49
  'update_epochs': 4
50
  'norm_adv': True
51
  'clip_coef': 0.2
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'rasyadanfz/LunarLander-v2-scratch'
58
+ 'batch_size': 2560
59
+ 'minibatch_size': 320}
60
  ```
61
 
logs/events.out.tfevents.1730790921.ae058a846904.1731.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2170cb90bdca5f9ca45d66ad85800f57b7ac5ce5814f5ddf335ed13e6fb62d
3
+ size 318671
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ece88af91db57a7c184adc8cad96eda322f09cfb1063880d65a62d5d97958eb1
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dbf00671a155baa33131196b6ec3cbe64afb7ec9084f5c73beaa84a4c29cbfa
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": -30.9154488721757, "std_reward": 28.711124128709596, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-05T04:35:45.727531"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 3.4693387284796002, "std_reward": 113.02136440581737, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-05T07:31:18.260024"}