FredericProtat commited on
Commit
f30242d
1 Parent(s): 2e8c8dc

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: 76.95 +/- 63.76
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: 77.38 +/- 66.24
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.1694627579.b693a32d7521.38408.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41f1bf052784900e33ab1668b5c3dcbc89c20fe12ee71fa76ebea6f48f86045
3
+ size 646762
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:524460df821d0e736d84cfae3109aadc7d2a4dcf093b630dfd059a274054b982
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb62b37cb54ab4f5f9f1b3cfa2bf07f8feb30120bb1dae232b89b082e432cd2
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": 76.95135054600244, "std_reward": 63.75963984093086, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T17:41:24.497979"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 77.38195338611227, "std_reward": 66.23722862757693, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T18:14:18.483430"}