jensenwiedler commited on
Commit
717c3d3
·
verified ·
1 Parent(s): fc3af43

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: -207.91 +/- 133.56
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': 100000
41
  'learning_rate': 0.00025
42
- 'num_envs': 16
43
- 'num_steps': 1024
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': 'jensenwiedler/ppo-LunarLander-v2-unit8'
58
- 'batch_size': 16384
59
- 'minibatch_size': 4096}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 11.62 +/- 80.51
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 1000000
41
  'learning_rate': 0.00025
42
+ 'num_envs': 4
43
+ 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'jensenwiedler/ppo-LunarLander-v2-unit8'
58
+ 'batch_size': 512
59
+ 'minibatch_size': 128}
60
  ```
61
 
logs/events.out.tfevents.1737225772.15778017b4a9.12115.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e94b7fee620b9f1b222da9b07dd4af10a0f7e39468fb18855709f3b25573b5d3
3
+ size 1255280
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40db81fd2835fcd4c965e800d7b5e91e89336b6b7133043e0939810c03226e00
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
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": -207.91236777986197, "std_reward": 133.56279763935407, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-18T18:39:30.869628"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 11.615449250978989, "std_reward": 80.51189109258232, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-18T19:13:09.066736"}