metadata
tag:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: PPO
results:
- metrics:
- type: mean_reward
value: '-121.77 +/- 30.58'
name: mean_reward
task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
# 使用PPO智能体来玩 LunarLander-v2
这是一个使用PPO训练有素的模型玩 LunarLander-v2.
要学习编写你自己的PPO智能体并训练它,
请查阅深度强化学习课程第8单元: https://github.com/huggingface/deep-rl-class/tree/main/unit8
# 超参数
```python
{'exp_name': 'ppo'
'seed': 1 'torch_deterministic': True 'cuda': True 'track': False 'wandb_project_name': 'cleanRL' 'wandb_entity': None 'capture_video': False 'env_id': 'LunarLander-v2' 'total_timesteps': 50000 'learning_rate': 0.00025 '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': 'sun1638650145/PyTorch-PPO-LunarLander-v2' 'batch_size': 512 'minibatch_size': 128} ```