Hanna Tochylina commited on
Commit
0c39134
1 Parent(s): 75e77bd

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: 47.01 +/- 43.01
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -38,14 +38,14 @@ model-index:
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 500000
41
- 'learning_rate': 0.00025
42
  'num_envs': 10
43
- 'num_steps': 512
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
- 'gae_lambda': 0.95
48
- 'num_minibatches': 16
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': 'Jupiterian9/ppo-LunarLander-v2'
58
- 'batch_size': 5120
59
- 'minibatch_size': 320}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 100.87 +/- 46.23
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 500000
41
+ 'learning_rate': 0.003
42
  'num_envs': 10
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
+ 'gae_lambda': 0.98
48
+ 'num_minibatches': 64
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': 'Jupiterian9/ppo-LunarLander-v2'
58
+ 'batch_size': 10240
59
+ 'minibatch_size': 160}
60
  ```
61
 
logs/events.out.tfevents.1680894099.f45d418bb99b.21150.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61393c56f151152bfd8d47bc87539038abbc36b48799b5e51e1d741e59e9ae5d
3
+ size 176519
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f22f175da6abb3fc0fe7dd0d634e9dd75ada6a343e3ed03048fd38d775de97b
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c66a22523ae37d706261c1d64f1303f556af89d1534f9f8f54a84101bdfa0728
3
  size 42597
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": 47.00978655213031, "std_reward": 43.011871889705716, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-07T18:55:39.674604"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 100.8712642876493, "std_reward": 46.225733289827936, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-07T19:12:09.914810"}