jlse commited on
Commit
e9bbcea
·
verified ·
1 Parent(s): 8043a65

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: -237.31 +/- 148.58
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': 50000
41
  'learning_rate': 1e-05
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': 'jlse/ppo-LunarLander-v2-u8'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -168.42 +/- 123.11
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 500000
41
  'learning_rate': 1e-05
42
+ 'num_envs': 8
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'jlse/ppo-LunarLander-v2-u8'
58
+ 'batch_size': 8192
59
+ 'minibatch_size': 2048}
60
  ```
61
 
logs/events.out.tfevents.1746352486.c76eb6dd0886.13880.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d79ea6c38e01008fef6c303d8f7a1b84e4843e4a4d0540e70ee371198174c2e4
3
+ size 670297
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0165ae158edfb9ce9a8e4f870c8574d4eca4548e295a6353948fe7bf94c0d49
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f379ad064956e760b48cd38a6e4f813c97f20e13615e3e7a7de1e701176055
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": -237.30623736980837, "std_reward": 148.57985030187143, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-04T09:49:05.171723"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -168.4181726221641, "std_reward": 123.11107128588853, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-04T09:58:24.574459"}