|
|
--- |
|
|
tags: |
|
|
- CartPole-v1 |
|
|
- ppo |
|
|
- deep-reinforcement-learning |
|
|
- reinforcement-learning |
|
|
- custom-implementation |
|
|
- deep-rl-course |
|
|
model-index: |
|
|
- name: PPO |
|
|
results: |
|
|
- task: |
|
|
type: reinforcement-learning |
|
|
name: reinforcement-learning |
|
|
dataset: |
|
|
name: CartPole-v1 |
|
|
type: CartPole-v1 |
|
|
metrics: |
|
|
- type: mean_reward |
|
|
value: 186.40 +/- 49.43 |
|
|
name: mean_reward |
|
|
verified: false |
|
|
--- |
|
|
|
|
|
# PPO Agent Playing CartPole-v1 |
|
|
|
|
|
This is a trained model of a PPO agent playing CartPole-v1. |
|
|
|
|
|
# Hyperparameters |
|
|
```python |
|
|
{'exp_name': 'unit8_part1', |
|
|
'gym_id': 'CartPole-v1', |
|
|
'learning_rate': 0.00025, |
|
|
'seed': 1, |
|
|
'total_timesteps': 100000, |
|
|
'torch_deterministic': True, |
|
|
'cuda': True, |
|
|
'track': False, |
|
|
'wandb_project_name': 'ppo-implementation-details', |
|
|
'wandb_entity': None, |
|
|
'capture_video': False, |
|
|
'num_envs': 4, |
|
|
'num_steps': 128, |
|
|
'anneal_lr': True, |
|
|
'gae': True, |
|
|
'gamma': 0.99, |
|
|
'gae_lambda': 0.95, |
|
|
'num_minibatches': 4, |
|
|
'update_epochs': 4, |
|
|
'norm_adv': True, |
|
|
'clip_coef': 0.2, |
|
|
'clip_vloss': True, |
|
|
'ent_coef': 0.01, |
|
|
'vf_coef': 0.5, |
|
|
'max_grad_norm': 0.5, |
|
|
'target_kl': None, |
|
|
'repo_id': 'tmoroder/ppo-CartPole-v1', |
|
|
'batch_size': 512, |
|
|
'minibatch_size': 128} |
|
|
``` |
|
|
|
