Ari8 commited on
Commit
20d01f9
·
verified ·
1 Parent(s): dcf91e1

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: -204.04 +/- 147.92
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': 50100
41
  'learning_rate': 0.0001
42
- 'num_envs': 4
43
- 'num_steps': 128
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': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -131.96 +/- 50.47
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 50000
41
  'learning_rate': 0.0001
42
+ 'num_envs': 6
43
+ 'num_steps': 256
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': 1536
59
+ 'minibatch_size': 384}
60
  ```
61
 
logs/events.out.tfevents.1746578021.b45e59692ef7.14129.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02cda2382eff2f2511d37d178d1bc54c698287c97e546571f65e1de557e670e0
3
+ size 78553
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a2f66e53a5cbeea0926832ba4016c267d5527db1f80735bb1e2fd971a055371
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c05d9d256b36cd51bfe315e184b9f458c6cd59a62dffd9046688282487e3849f
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": -204.03906121406425, "std_reward": 147.91532939751013, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:28:37.542593"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -131.95602190446917, "std_reward": 50.465530849682274, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:34:11.173245"}