Sam017 commited on
Commit
0a08a0a
·
verified ·
1 Parent(s): 320753d

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: -37.19 +/- 62.35
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -39,7 +39,7 @@ model-index:
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 1000000
41
  'learning_rate': 0.00025
42
- 'num_envs': 8
43
  'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
@@ -48,14 +48,14 @@ model-index:
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
51
- 'clip_coef': 0.2
52
  'clip_vloss': True
53
  'ent_coef': 0.01
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Sam017/ppo-CartPole-v1'
58
- 'batch_size': 8192
59
- 'minibatch_size': 2048}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -98.97 +/- 68.99
21
  name: mean_reward
22
  verified: false
23
  ---
 
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
 
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
51
+ 'clip_coef': 0.5
52
  'clip_vloss': True
53
  'ent_coef': 0.01
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Sam017/ppo-CartPole-v1'
58
+ 'batch_size': 16384
59
+ 'minibatch_size': 4096}
60
  ```
61
 
logs/events.out.tfevents.1750885114.f8d56c68b18d.11769.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29acd88f26c85446ef28ec1305d4658acf30fd51497a38df7ae153fd52a89e4a
3
+ size 924136
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89eeb9741c0df07e120137d1359b8b165c500264cb318622b64ef1e154338f3d
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab62512b99c2fa4f992bbfaa1abc3df2cfd4904b1e1abb7b45d6d6a7ce45f5ac
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": -37.188726761319955, "std_reward": 62.352263463181515, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-25T20:54:27.983010"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -98.9690545146643, "std_reward": 68.99165614559064, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-25T21:04:38.219276"}