Playing with the learnt Q-table

playing_q_table.py

# Reset environment
state = env.reset()

# Render it
env.render()
time.sleep(0.5)

done = False
while not done:
    # Choose the action with the max expected reward i.e. max Q-value
    action = np.argmax(q_table[state])
    # Try it !
    state, reward, done, info = env.step(action)
    # See the result
    clear_output(wait=True)
    env.render()
    print(reward)
    time.sleep(0.5)