ลูปการฝึก DRL

env = gym.make("LunarLander-v2")
# Run ten episodes
for episode in ____:
    state, info = env.reset()
    done = False    
    # Run through steps until done
    while ____:
        action = select_action(network, state)        
        # Take the action
        next_state, reward, terminated, truncated, _ = ____
        done = terminated or truncated        
        loss = calculate_loss(network, state, action, next_state, reward, done)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()        
        # Update the state
        state = ____
    print(f"Episode {episode} complete.")