candrews1971 commited on
Commit
fabf221
1 Parent(s): c3a92dd

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: 0.83 +/- 0.70
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -28,7 +28,7 @@ model-index:
28
 
29
  # Hyperparameters
30
  ```python
31
- {'exp_name': 'LongRunningOriginal'
32
  'seed': 1
33
  'torch_deterministic': True
34
  'cuda': True
@@ -37,16 +37,16 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': True
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 4000000
41
- 'learning_rate': 0.00025
42
- 'num_envs': 8
43
- 'num_steps': 1024
44
  'anneal_lr': False
45
  'gae': True
46
  'gamma': 0.999
47
  'gae_lambda': 0.98
48
  'num_minibatches': 4
49
- 'update_epochs': 4
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
@@ -57,7 +57,7 @@ model-index:
57
  'num_hidden_layers': 2
58
  'upload_to_hf': True
59
  'repo_id': 'candrews1971/ppo-LunarLander-v2.1'
60
- 'batch_size': 8192
61
- 'minibatch_size': 2048}
62
  ```
63
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 0.60 +/- 1.00
21
  name: mean_reward
22
  verified: false
23
  ---
 
28
 
29
  # Hyperparameters
30
  ```python
31
+ {'exp_name': '3million'
32
  'seed': 1
33
  'torch_deterministic': True
34
  'cuda': True
 
37
  'wandb_entity': None
38
  'capture_video': True
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 3000000
41
+ 'learning_rate': 0.0004
42
+ 'num_envs': 4
43
+ 'num_steps': 128
44
  'anneal_lr': False
45
  'gae': True
46
  'gamma': 0.999
47
  'gae_lambda': 0.98
48
  'num_minibatches': 4
49
+ 'update_epochs': 16
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
 
57
  'num_hidden_layers': 2
58
  'upload_to_hf': True
59
  'repo_id': 'candrews1971/ppo-LunarLander-v2.1'
60
+ 'batch_size': 512
61
+ 'minibatch_size': 128}
62
  ```
63
 
logs/events.out.tfevents.1718372382.ChrisGaming.800938.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90a1e071bc7b118ed577dfeb76dfa83035ccf5b3ed276da0f325db0b4d3f7db
3
+ size 4204279
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a28348f6869672d4de87040cbef9f4538bbaee7501b85bb2b303fbb89a1b7306
3
  size 77182
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0875cf7cf0f752770c79a2667d0c0287a45f688bdc59162badd0a3d3ae1cd84c
3
  size 77182
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": 0.826945648767448, "std_reward": 0.6998308608742364, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-13T19:20:38.468262"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 0.6009258633768677, "std_reward": 0.9958946932658063, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-14T09:29:42.108499"}