daishan986 commited on
Commit
42dc404
·
verified ·
1 Parent(s): 34d1165

Push agent to the Hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -17,7 +17,7 @@ model-index:
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
- value: 170.82 +/- 100.73
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': 1500000
41
  'learning_rate': 0.0003
42
- 'num_envs': 4
43
- 'num_steps': 512
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': 'daishan986/ppo-LunarLander-v2'
58
- 'batch_size': 2048
59
- 'minibatch_size': 512}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 149.76 +/- 107.22
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 4000000
41
  'learning_rate': 0.0003
42
+ 'num_envs': 8
43
+ 'num_steps': 2048
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'daishan986/ppo-LunarLander-v2'
58
+ 'batch_size': 16384
59
+ 'minibatch_size': 4096}
60
  ```
61
 
logs/events.out.tfevents.1760175951.daishanM3Max.local.5304.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3288279c2547191265855036b26b804c284684a737a95d7dd348b5eae18efdbd
3
+ size 127460
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2dc3ab94a33bd1f1f5af93b3f3401c8d66d666b57fcc391c96e7ddcaa48c37f
3
  size 43291
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ca05ae453dd6e87f45870d34d94e48cde03888c054482ea5b14b03fceaad71
3
  size 43291
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": 170.8158490059879, "std_reward": 100.72984635836627, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-11T17:44:04.735430"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 149.75875121440114, "std_reward": 107.21560522096156, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-11T17:50:20.232486"}