Views
No views yet
policy.pth – Trained PPO policy weights (PyTorch).ppo_policy.zip – Stable-Baselines3 PPO saved model (reload with PPO.load()).safe_policy_meta.json – Metadata for policy compliance.best/ – Best checkpointed model during training.eval_logs/ – Evaluation logs.tb_logs/ – TensorBoard logs.1from stable_baselines3 import PPO
2import gymnasium as gym
3
4# Load model
5model = PPO.load("ppo_policy.zip")
6
7# Example run
8env = gym.make("CartPole-v1")
9obs, _ = env.reset()
10action, _ = model.predict(obs)
11print("Predicted action:", action)