Melatih algoritma A2C

Saatnya melatih Lunar Lander kita menggunakan algoritma A2C! Anda sudah memiliki seluruh komponen, kini saatnya menyusunnya menjadi satu kesatuan.

Jaringan actor dan critic telah diinstansiasi sebagai actor dan critic, begitu pula optimizer-nya actor_optimizer dan critic_optimizer.

Fungsi REINFORCE select_action() dan fungsi calculate_losses() dari latihan sebelumnya juga tersedia untuk Anda gunakan di sini.

Latihan ini adalah bagian dari kursus

Deep Reinforcement Learning dengan Python

Petunjuk latihan

Biarkan actor memilih aksi berdasarkan state.
Hitung loss untuk actor dan critic.

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

for episode in range(10):
    state, info = env.reset()
    done = False
    episode_reward = 0
    step = 0
    while not done:
        step += 1
        if done:
            break
        # Select the action
        ____
        next_state, reward, terminated, truncated, _ = env.step(action)
        done = terminated or truncated
        episode_reward += reward
        # Calculate the losses
        ____, ____ = ____(
            critic, action_log_prob, 
            reward, state, next_state, done)        
        actor_optimizer.zero_grad()
        actor_loss.backward()
        actor_optimizer.step()
        critic_optimizer.zero_grad()
        critic_loss.backward()
        critic_optimizer.step()
        state = next_state
    describe_episode(episode, reward, episode_reward, step)

Edit dan Jalankan Kode

Latihan ini adalah bagian dari kursus

Deep Reinforcement Learning dengan Python

SkillTag.level.advancedSkillTag.label

4.8+

Mulai Kursus Gratis

Discover how deep reinforcement learning improves upon traditional Reinforcement Learning while studying and implementing your first Deep Q Learning algorithm.

Exercise 1: Introduction to deep reinforcement learning Exercise 2: Environment and neural network setup Exercise 3: DRL training loop Exercise 4: Introduction to deep Q learning Exercise 5: Deep learning and DQN Exercise 6: The Q-Network architecture Exercise 7: Instantiating the Q-Network Exercise 8: The barebone DQN algorithm Exercise 9: Barebone DQN action selection Exercise 10: Barebone DQN loss function Exercise 11: Training the barebone DQN

Dive into Deep Q-learning by implementing the original DQN algorithm, featuring Experience Replay, epsilon-greediness and fixed Q-targets. Beyond DQN, you will then explore two fascinating extensions that improve the performance and stability of Deep Q-learning: Double DQN and Prioritized Experience Replay.

Exercise 1: DQN with experience replay Exercise 2: The double-ended queue Exercise 3: Experience replay buffer Exercise 4: DQN with experience replay Exercise 5: The complete DQN algorithm Exercise 6: Epsilon-greediness Exercise 7: Fixed Q-targets Exercise 8: Implementing the complete DQN algorithm Exercise 9: Double DQN Exercise 10: Online network and target network in DDQN Exercise 11: Training the double DQN Exercise 12: Prioritized experience replay Exercise 13: Prioritized experience replay buffer Exercise 14: Sampling from the PER buffer Exercise 15: DQN with prioritized experience replay

Learn about the foundational concepts of policy gradient methods found in DRL. You will begin with the policy gradient theorem, which forms the basis for these methods. Then, you will implement the REINFORCE algorithm, a powerful approach to learning policies. The chapter will then guide you through Actor-Critic methods, focusing on the Advantage Actor-Critic (A2C) algorithm, which combines the strengths of both policy gradient and value-based methods to enhance learning efficiency and stability.

Exercise 1: Pengantar policy gradient Exercise 2: Arsitektur policy network Exercise 3: Bekerja dengan distribusi diskret Exercise 4: Policy gradient dan REINFORCE Exercise 5: Pemilihan aksi dalam REINFORCE Exercise 6: Melatih algoritma REINFORCE Exercise 7: Advantage Actor-Critic Exercise 8: Jaringan critic Exercise 9: Perhitungan rugi Actor-Critic Exercise 10: Melatih algoritma A2C

Latihan Saat Ini

Explore Proximal Policy Optimization (PPO) for robust DRL performance. Next, you will examine using an entropy bonus in PPO, which encourages exploration by preventing premature convergence to deterministic policies. You'll also learn about batch updates in policy gradient methods. Finally, you will learn about hyperparameter optimization with Optuna, a powerful tool for optimizing performance in your DRL models.

Exercise 1: Proximal policy optimization Exercise 2: The clipped probability ratio Exercise 3: The clipped surrogate objective function Exercise 4: Entropy bonus and PPO Exercise 5: Entropy playground Exercise 6: Training the PPO algorithm Exercise 7: Batch updates in policy gradient Exercise 8: Minibatch and DRL Exercise 9: A2C with batch updates Exercise 10: Hyperparameter optimization with Optuna Exercise 11: Hyperparameter or not?Exercise 12: Hands-on with Optuna Exercise 13: Congratulations!