BabyRobotEnv_v5_RL_loop.py

# run the environment, taking random actions
env.reset()

info = {}
terminated = False
while not terminated:

  # choose a random action
  action = env.action_space.sample()

  # take the action and get the information from the environment
  new_state, reward, terminated, truncated, info = env.step(action)

  # form an information string
  info_str = f"{Actions(action): <5}: {new_state} reward = {reward}"

  # show the current position and reward
  env.render(info = {'side_info': [((10,10),info_str)]})