|
--- |
|
library_name: stable-baselines3 |
|
tags: |
|
- LunarLander-v2 |
|
- deep-reinforcement-learning |
|
- reinforcement-learning |
|
- stable-baselines3 |
|
model-index: |
|
- name: PPO |
|
results: |
|
- task: |
|
type: reinforcement-learning |
|
name: reinforcement-learning |
|
dataset: |
|
name: LunarLander-v2 |
|
type: LunarLander-v2 |
|
metrics: |
|
- type: mean_reward |
|
value: 242.40 +/- 15.91 |
|
name: mean_reward |
|
verified: false |
|
--- |
|
|
|
# **PPO** Agent playing **LunarLander-v2** |
|
This model is trained using **PPO [proximal policy optimization algorithm invented by OpenAI]** The RL-based agent playing to land correctly on the moon using **LunarLander** environment as simulator. |
|
|
|
## Usage (with Stable-baselines3) |
|
TODO: Add your code |
|
|
|
|
|
```python |
|
from stable_baselines3 import ... |
|
from huggingface_sb3 import load_from_hub |
|
|
|
repo_id = "innocent-charles/RL-ppo-LunarLander-v2" |
|
filename = "RL-ppo-LunarLander-v2.zip" |
|
|
|
custom_objects = { |
|
"learning_rate": 0.0, |
|
"lr_schedule": lambda _: 0.0, |
|
"clip_range": lambda _: 0.0, |
|
} |
|
|
|
checkpoint = load_from_hub(repo_id, filename) |
|
model = PPO.load(checkpoint, custom_objects=custom_objects, print_system_info=True) |
|
|
|
... |
|
``` |
|
|
