Hugging Face's logo

tmoroder
/
ppo-CartPole-v1

Reinforcement Learning
TensorBoard
CartPole-v1
ppo
deep-reinforcement-learning
custom-implementation
deep-rl-course
Eval Results
Model card Files
xet
Metrics Community
tmoroder commited on
Commit
bed52ae
·
verified ·
1 Parent(s): 70d19dd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -28
README.md CHANGED
@@ -29,33 +29,33 @@ model-index:
29
  # Hyperparameters
30
  ```python
31
  {'exp_name': 'unit8_part1',
32
- 'gym_id': 'CartPole-v1',
33
- 'learning_rate': 0.00025,
34
- 'seed': 1,
35
- 'total_timesteps': 50000,
36
- 'torch_deterministic': True,
37
- 'cuda': True,
38
- 'track': False,
39
- 'wandb_project_name': 'ppo-implementation-details',
40
- 'wandb_entity': None,
41
- 'capture_video': False,
42
- 'num_envs': 4,
43
- 'num_steps': 128,
44
- 'anneal_lr': True,
45
- 'gae': True,
46
- 'gamma': 0.99,
47
- 'gae_lambda': 0.95,
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': 'tmoroder/ppo-CartPole-v1',
58
- 'batch_size': 512,
59
- 'minibatch_size': 128}
60
  ```
61
 
 
29
  # Hyperparameters
30
  ```python
31
  {'exp_name': 'unit8_part1',
32
+ 'gym_id': 'CartPole-v1',
33
+ 'learning_rate': 0.00025,
34
+ 'seed': 1,
35
+ 'total_timesteps': 50000,
36
+ 'torch_deterministic': True,
37
+ 'cuda': True,
38
+ 'track': False,
39
+ 'wandb_project_name': 'ppo-implementation-details',
40
+ 'wandb_entity': None,
41
+ 'capture_video': False,
42
+ 'num_envs': 4,
43
+ 'num_steps': 128,
44
+ 'anneal_lr': True,
45
+ 'gae': True,
46
+ 'gamma': 0.99,
47
+ 'gae_lambda': 0.95,
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': 'tmoroder/ppo-CartPole-v1',
58
+ 'batch_size': 512,
59
+ 'minibatch_size': 128}
60
  ```
61