Training a PPO model on Pendulum

train.py

import gym

from stable_baselines import PPO1
from stable_baselines.common.policies import MlpPolicy
from stable_baselines.common.callbacks import EvalCallback

env = gym.make('Pendulum-v0')
model = PPO1(MlpPolicy, env)

# Separate evaluation env
eval_env = gym.make('Pendulum-v0')
eval_callback = EvalCallback(eval_env, best_model_save_path='./logs/',
                             log_path='./logs/', eval_freq=500,
                             deterministic=True, render=False)

model.learn(5000, callback=eval_callback)