FredericProtat commited on
Commit
f364ebb
·
1 Parent(s): 6ddc208

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: -143.69 +/- 45.82
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: -153.92 +/- 49.78
21
  name: mean_reward
22
  verified: false
23
  ---
 
41
  'capture_video': False
42
  'env_id': 'LunarLander-v2'
43
  'num_envs': 4
44
+ 'num_steps': 128
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': 512
60
+ 'minibatch_size': 128}
61
  ```
62
 
logs/events.out.tfevents.1694596608.422f4b7e0f84.5041.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d0d13fb1cd719e1f2c7a41b5ddd904b3361c7b34475f7c610a65c900d5dc56
3
+ size 232146
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 sha256:385c638c8ae522ee4059713cd3787fd9992ba9a9e3f051f8d69081c43fc75cdf
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": -143.6929609029077, "std_reward": 45.82422281682007, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:15:18.637476"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -153.9228011894701, "std_reward": 49.7759966909385, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:17:55.742216"}