Marc-Elie commited on
Commit
ede7710
1 Parent(s): 6da36d8

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: -69.37 +/- 79.56
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,13 +37,13 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 100000
41
- 'learning_rate': 0.001
42
- 'num_envs': 16
43
  'num_steps': 164
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.995
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Marc-Elie/LunarLander-v2-3'
58
- 'batch_size': 2624
59
- 'minibatch_size': 656}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 7.02 +/- 59.97
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 200000
41
+ 'learning_rate': 0.0005
42
+ 'num_envs': 8
43
  'num_steps': 164
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.999
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Marc-Elie/LunarLander-v2-3'
58
+ 'batch_size': 1312
59
+ 'minibatch_size': 328}
60
  ```
61
 
logs/events.out.tfevents.1684162152.5fc12f631080.27391.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:412cbfc52e1f516864737de16262cd673ed552bea9401109608688a5d551c2d3
3
+ size 78904
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e97716f1c1821d74e386875b0c84f2ae92b12d78f46463788c5c6fb81dedbee4
3
  size 42469
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841654808b9bd8e1980530232abbcf7a20124acba16e1ca86d01e0a36f22b258
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": -69.36928426855437, "std_reward": 79.55686832901321, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-15T14:47:29.133401"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 7.015737442433943, "std_reward": 59.973310137534206, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-15T14:53:21.729194"}