drap/cartpole-ppo

PPO CartPole Agent

This is a PPO agent trained on the CartPole-v1 environment using Stable Baselines3.

Performance

The agent achieved a mean reward of 500.00 ± 0.00 over 10 evaluation episodes.

Training Details

• Algorithm: PPO
• Environment: CartPole-v1
• Training Steps: 25,000
• Framework: Stable Baselines3

Usage

from stable_baselines3 import PPO
import gymnasium as gym

# Load the model
model = PPO.load("drap/cartpole-ppo")

# Create environment
env = gym.make("CartPole-v1")

# Test the model
obs, _ = env.reset()
while True:
    action, _ = model.predict(obs, deterministic=True)
    obs, reward, terminated, truncated, _ = env.step(action)
    if terminated or truncated:
        break