Hands-On Q-Learning with Python

Stepping through actions

We can take a random action using env.action_space.sample(), as follows:

observation, reward, done, info = env.step(env.action_space.sample())

The env.action_space.sample() function returns a random action from the allowed actions. The env.step() function carries out this action and sends us to the next state.

Recall the four variables that we have collected from env.step():

• observation: This refers to the new state that we are in.
• reward: This indicates the reward that we have received.
• done: This tells us whether we have successfully dropped off the passenger at the correct location or whether we have taken the maximum number of steps.
• info: This provides additional information that we may need for debugging. ...