FredericProtat commited on
Commit
da963f6
·
1 Parent(s): 8568324

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: 276.09 +/- 20.19
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': 256
45
  'anneal_lr': True
46
  'gae': True
47
  'gamma': 0.999
@@ -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': 1024
60
- 'minibatch_size': 256}
61
  ```
62
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 255.89 +/- 13.95
21
  name: mean_reward
22
  verified: false
23
  ---
 
41
  'capture_video': False
42
  'env_id': 'LunarLander-v2'
43
  'num_envs': 4
44
+ 'num_steps': 512
45
  'anneal_lr': True
46
  'gae': True
47
  'gamma': 0.999
 
56
  'max_grad_norm': 0.5
57
  'target_kl': None
58
  'repo_id': 'FredericProtat/ppo-LunarLander-v2'
59
+ 'batch_size': 2048
60
+ 'minibatch_size': 512}
61
  ```
62
 
logs/events.out.tfevents.1694686682.586a4fb82a8c.2256.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d0c3aed4b796f09bcd9558956ed79253b10f786568341a292df3ccb5b83fc49
3
+ size 2763711
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3347ecae991e04763a6e029e1fb79738e161c97f733a1b0c7af0f6082dadce6
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08adc4f22dd9c65dcdff08333571dd223fac3cee8e713dffe3705e7da86607b8
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": 276.08997855741995, "std_reward": 20.188224795713282, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T19:47:39.065764"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 255.89097883627375, "std_reward": 13.94997954387589, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-14T12:05:30.621901"}