FredericProtat commited on
Commit
202cf62
·
1 Parent(s): c42bf0e

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: -169.75 +/- 58.70
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -41,7 +41,7 @@ model-index:
41
  'capture_video': False
42
  'env_id': 'LunarLander-v2'
43
  'num_envs': 4
44
- 'num_steps': 1024
45
  'anneal_lr': True
46
  'gae': True
47
  'gamma': 0.99
@@ -56,7 +56,7 @@ model-index:
56
  'max_grad_norm': 0.5
57
  'target_kl': None
58
  'repo_id': 'FredericProtat/ppo-LunarLander-v2'
59
- 'batch_size': 4096
60
- 'minibatch_size': 1024}
61
  ```
62
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -137.34 +/- 71.66
21
  name: mean_reward
22
  verified: false
23
  ---
 
41
  'capture_video': False
42
  'env_id': 'LunarLander-v2'
43
  'num_envs': 4
44
+ 'num_steps': 2048
45
  'anneal_lr': True
46
  'gae': True
47
  'gamma': 0.99
 
56
  'max_grad_norm': 0.5
57
  'target_kl': None
58
  'repo_id': 'FredericProtat/ppo-LunarLander-v2'
59
+ 'batch_size': 8192
60
+ 'minibatch_size': 2048}
61
  ```
62
 
logs/events.out.tfevents.1694597029.422f4b7e0f84.6828.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de02245d9972b4ca41c520202f0dfde7b051b51bd1c8f35df572302d44e18d6d
3
+ size 134458
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01325302399cb8ec0d889634e3b29571aec79c0e7ea6c790ac700c6759a289e7
3
  size 42469
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b070ac4d259a1f36b1b3dd182d6008d511239b0c819265de862eea81a38debb5
3
  size 42469
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": -169.74604938966104, "std_reward": 58.702347317400466, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:22:47.355900"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -137.33631788087882, "std_reward": 71.65741332660649, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:24:40.736619"}