bnowak1831 commited on
Commit
8926a34
1 Parent(s): 74c9cc2

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: -107.47 +/- 62.56
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -39,7 +39,7 @@ model-index:
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 50000
41
  'learning_rate': 0.0002
42
- 'num_envs': 4
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'bnowak1831/pp0-LunarLander-v2'
58
- 'batch_size': 512
59
- 'minibatch_size': 32}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -125.15 +/- 69.78
21
  name: mean_reward
22
  verified: false
23
  ---
 
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 50000
41
  'learning_rate': 0.0002
42
+ 'num_envs': 16
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'bnowak1831/pp0-LunarLander-v2'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 128}
60
  ```
61
 
logs/events.out.tfevents.1677612598.f57ae78282d8.14700.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46107d618e40e23e2430c868e48d3aefa3472246f8a117b4f3630a93d0af4bd4
3
+ size 67504
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f19bbd2716a451c998c74afb744675c825defabf31f87b60b9dedbdbe625eb4
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6206123bbf8c56fe9de836b2f0e53c2d4e34c399c78b302eb5732d99b1879aa
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": -107.47009749999802, "std_reward": 62.55842960025507, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-28T19:28:27.259343"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -125.1508832560572, "std_reward": 69.77922273942967, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-28T19:30:27.906109"}