PPO Agent playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library.
Usage (with Stable-baselines3)
TODO: Add your code
import gym
from stable_baselines3 import PPO
from stable_baselines3.common.vec_env import DummyVecEnv
from stable_baselines3.common.env_util import make_vec_env
from huggingface_sb3 import package_to_hub
from huggingface_sb3 import load_from_hub
repo_id = "raghuvamsidhar/ppo-LunarLander-v2" # The repo_id
filename = "PPO-LunarLander-v2-RVD.zip" # The model filename.zip
# When the model was trained on Python 3.8 the pickle protocol is 5
# But Python 3.6, 3.7 use protocol 4
# In order to get compatibility we need to:
# 1. Install pickle5 (we done it at the beginning of the colab)
# 2. Create a custom empty object we pass as parameter to PPO.load()
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)
...
- Downloads last month
- 0
Evaluation results
- mean_reward on LunarLander-v2self-reported284.82 +/- 13.27