Example of Gymnasium usage using random actions

cart-pole-example.py

import gymnasium as gym

env = gym.make("CartPole-v1")
observation, info = env.reset(seed=42)

for iteration in range(1000):
    action = env.action_space.sample()  # this is where you would insert your policy
    observation, reward, terminated, truncated, info = env.step(action)

    print('Current iteration: ', iteration)
    print('Current state: ', observation)
    print('Action taken: ', action)
    print()

    if terminated or truncated:
        observation, info = env.reset()

env.close()