yuval6967 commited on
Commit
c192e23
1 Parent(s): e108128

Push agent to the Hub

Browse files
README.md CHANGED
@@ -17,7 +17,7 @@ model-index:
17
  type: CartPole-v1
18
  metrics:
19
  - type: mean_reward
20
- value: 273.90 +/- 153.17
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -38,7 +38,7 @@ model-index:
38
  'capture_video': False
39
  'env_id': 'CartPole-v1'
40
  'total_timesteps': 50000
41
- 'learning_rate': 0.0003
42
  'num_envs': 4
43
  'num_steps': 128
44
  'anneal_lr': True
@@ -50,10 +50,10 @@ model-index:
50
  'norm_adv': True
51
  'clip_coef': 0.05
52
  'clip_vloss': True
53
- 'ent_coef': 0.0001
54
  'vf_coef': 0.5
55
- 'max_grad_norm': 0.5
56
- 'target_kl': 0.01
57
  'repo_id': 'yuval6967/cart2PPO'
58
  'batch_size': 512
59
  'minibatch_size': 128}
 
17
  type: CartPole-v1
18
  metrics:
19
  - type: mean_reward
20
+ value: 234.20 +/- 89.02
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'env_id': 'CartPole-v1'
40
  'total_timesteps': 50000
41
+ 'learning_rate': 0.00025
42
  'num_envs': 4
43
  'num_steps': 128
44
  'anneal_lr': True
 
50
  'norm_adv': True
51
  'clip_coef': 0.05
52
  'clip_vloss': True
53
+ 'ent_coef': 0.01
54
  'vf_coef': 0.5
55
+ 'max_grad_norm': 0.1
56
+ 'target_kl': None
57
  'repo_id': 'yuval6967/cart2PPO'
58
  'batch_size': 512
59
  'minibatch_size': 128}
logs/events.out.tfevents.1685094891.2850cb3f29b2.24173.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b50d68e84143c7b1f97050c449f8fc049e926001fecfa62aea911f0f5383d9c2
3
+ size 113898
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f088edcd803bedc66b86c54da407d3144728e96760c45f0697f656ce925fb793
3
  size 40037
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f0da3d36e15a6df0c584df92c0574508c8f29bdd2e80375f040523581881a5
3
  size 40037
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "CartPole-v1", "mean_reward": 273.9, "std_reward": 153.17470417794186, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:53:48.498042"}
 
1
+ {"env_id": "CartPole-v1", "mean_reward": 234.2, "std_reward": 89.01550426751511, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:55:25.601685"}