MarkieMark1 commited on
Commit
a8e197b
1 Parent(s): f50bb5a

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: -92.89 +/- 58.78
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,14 +37,14 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 50000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
- 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.99
47
- 'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'MarkieMark1/ppo-LunarLander-v2'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 11.11 +/- 23.58
21
  name: mean_reward
22
  verified: false
23
  ---
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 1000000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.999
47
+ 'gae_lambda': 0.98
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'MarkieMark1/ppo-LunarLander-v2'
58
+ 'batch_size': 4096
59
+ 'minibatch_size': 1024}
60
  ```
61
 
logs/events.out.tfevents.1680091151.d14e7ab57ebc.8622.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a25b6a09ed3573ea0fb7ddca9f32e30150a97ce191ea16385a84ac062442b57
3
+ size 126325
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0762c60b8952f57601a85c2d5d3d6f6e862f4cc07ba530b06e3bd7b2d806a2a3
3
  size 42597
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:317cd561066c2d4bdb9a8401704aff44cd16fd2fee75a55af4e842b2442ce342
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": -92.88840155772964, "std_reward": 58.77776171800043, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-17T09:42:36.454775"}
1
+ {"env_id": "LunarLander-v2", "mean_reward": 11.110597383926264, "std_reward": 23.57757170909709, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-29T12:13:07.198507"}