drakrig commited on
Commit
c40f877
·
verified ·
1 Parent(s): 0e2bce0

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: -142.30 +/- 101.11
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': 0.00025
42
  'num_envs': 16
43
- 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.97
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'drakrig/LunarLander-v2-self'
58
- 'batch_size': 2048
59
- 'minibatch_size': 512}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 19.51 +/- 63.72
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': 0.00025
42
  'num_envs': 16
43
+ 'num_steps': 64
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.97
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'drakrig/LunarLander-v2-self'
58
+ 'batch_size': 1024
59
+ 'minibatch_size': 256}
60
  ```
61
 
logs/events.out.tfevents.1710579505.7fe4ccffaf5a.20242.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ebd17150444309e95a9fb8015c5f07ac45ba5d1cd7c81ea057d766aece5d1e9
3
+ size 502095
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cee94989e40f3c46f31e0bc5459ce93696be7d49629aabec1786c4562562c44
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a859dbee9c7750503d0a1284a49d813a2681e0385aeb788ca8caa547eb9abb21
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": -142.29617103374352, "std_reward": 101.10889573602778, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-16T08:57:25.575417"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 19.506833703494664, "std_reward": 63.71884576892275, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-16T09:05:09.651991"}