การนำ Double Q-learning ไปใช้

Q = [np.zeros((num_states, num_actions))] * 2
for episode in range(num_episodes):
    state, info = env.reset()
    terminated = False   
    while not terminated:
        action = np.random.choice(num_actions)
        next_state, reward, terminated, truncated, info = env.step(action)
        # Update the Q-tables
        ____
        state = next_state
# Combine the learned Q-tables        
Q = ____
policy = {state: np.argmax(Q[state]) for state in range(num_states)}
render_policy(policy)