Ari8 commited on
Commit
9e03608
·
verified ·
1 Parent(s): 6c6ba62

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: -127.93 +/- 86.57
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -38,9 +38,9 @@ model-index:
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 50000
41
- 'learning_rate': 1.5e-05
42
  'num_envs': 6
43
- 'num_steps': 256
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': None
57
  'repo_id': 'Ari8/ppo-LunarLander-v2_unit8'
58
- 'batch_size': 1536
59
- 'minibatch_size': 384}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -135.40 +/- 117.23
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 50000
41
+ 'learning_rate': 1e-05
42
  'num_envs': 6
43
+ 'num_steps': 365
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Ari8/ppo-LunarLander-v2_unit8'
58
+ 'batch_size': 2190
59
+ 'minibatch_size': 547}
60
  ```
61
 
logs/events.out.tfevents.1746578410.b45e59692ef7.15925.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27aae9cd43124e4f0199d61855a53a0737f51c30c3d21b936d22eaa4a6293481
3
+ size 73419
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64ce3d8291cb958b4b58580f27c404db6ee56893368457e61bc5d4cc3c1cd2b3
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce0b02aafd6a0569cd42539fb755bd4e0659ed596cc06ef557e5c37010c7d2c
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": -127.93070919552201, "std_reward": 86.57261284016951, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:38:30.149708"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -135.39870510537992, "std_reward": 117.23197675409425, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:40:40.064007"}