ben-yu commited on
Commit
25d4dcb
1 Parent(s): e19f02b

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: -131.13 +/- 79.07
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': 1000000
41
- 'learning_rate': 2.5e-05
42
- 'num_envs': 12
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': 'ben-yu/LunarLander-v2-ppo'
58
- 'batch_size': 1536
59
- 'minibatch_size': 384}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -157.31 +/- 149.85
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 1000000
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
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'ben-yu/LunarLander-v2-ppo'
58
+ 'batch_size': 16384
59
+ 'minibatch_size': 4096}
60
  ```
61
 
logs/events.out.tfevents.1676774045.5e7fcccfc678.7185.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69fcafaa3ec0bb2e5b6ab0ad46383f090abc2945dabb5475002e68296e0aac0b
3
+ size 1069313
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cd4b85914899feb9d2bbeef24aca091a6ac6bc11c04b585454d2908bfea22e8
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6444902951740fb78da7b5b51fb5ccd48eb21ee467064a2e5ff121b1655243
3
  size 42597
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": -131.13230129684894, "std_reward": 79.06856915869395, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T02:31:13.899828"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -157.3052475209271, "std_reward": 149.851983031017, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T02:40:00.886251"}