miki030 commited on
Commit
f9a6b74
·
1 Parent(s): d9ff87f

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: -129.04 +/- 112.39
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -50,10 +50,10 @@ model-index:
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
53
- 'ent_coef': 0.02
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.2
56
- 'target_kl': 0.015
57
  'repo_id': 'miki030/lunar2'
58
  'batch_size': 8192
59
  'minibatch_size': 2048}
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -134.24 +/- 65.69
21
  name: mean_reward
22
  verified: false
23
  ---
 
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
53
+ 'ent_coef': 0.001
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.2
56
+ 'target_kl': None
57
  'repo_id': 'miki030/lunar2'
58
  'batch_size': 8192
59
  'minibatch_size': 2048}
logs/events.out.tfevents.1693213087.d39058c94989.24364.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7637037c5764f5a5c601e1959485819a76c71a4afc50bdff6efeb1292978dc7
3
+ size 383068
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd2543fcfcf02d6fc8a4d545c00a48e93704a2929f9a41d16b5eb5371483f930
3
- size 8494437
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b4a220afb361ece27c8fc0ab6fab2752a22d6502a59db538f42dee477a2b8d
3
+ size 12693275
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": -129.04191177884766, "std_reward": 112.3893775242826, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-28T08:44:18.617629"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -134.23844033225845, "std_reward": 65.68831749910065, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-28T09:00:17.036184"}