maavaneck commited on
Commit
5dc6be7
·
verified ·
1 Parent(s): 576c563

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: -73.65 +/- 93.64
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,10 +37,10 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 1000000
41
  'learning_rate': 0.0005
42
  'num_envs': 4
43
- 'num_steps': 5000
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': 0.01
57
  'repo_id': 'maavaneck/cppo-LunarLander-v2'
58
- 'batch_size': 20000
59
- 'minibatch_size': 5000}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -58.17 +/- 87.37
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 2000000
41
  'learning_rate': 0.0005
42
  'num_envs': 4
43
+ 'num_steps': 8000
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': 0.01
57
  'repo_id': 'maavaneck/cppo-LunarLander-v2'
58
+ 'batch_size': 32000
59
+ 'minibatch_size': 8000}
60
  ```
61
 
logs/events.out.tfevents.1727770874.bf4fa99681ff.9959.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674df00f28bb114c40b772bf013272a12a8c4c257512ffe2d8ecd0fa50342a83
3
+ size 1072565
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97554e3ae4a3918920115714d53a505fa82080235052c49c1a33b1c1b806f87a
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca1fd9b230975455d80ba5f121bf6bb7bc951b519204e277e8a4625d8aea19b
3
  size 43026
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": -73.64973154359474, "std_reward": 93.63768838165115, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-01T08:16:34.742726"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -58.17063860081388, "std_reward": 87.36857573228411, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-01T08:52:07.248331"}