Temel DQN eylem seçimi

select_action() fonksiyonu, her adımda en yüksek Q-değerine sahip eylemi seçmeni sağlar.

Fonksiyon, argüman olarak Q-ağını ve mevcut durumu alır ve en yüksek Q-değerine sahip eylemin indeksini döndürür.

Q-ağı q_network olarak örneklenmiştir ve üzerinde çalışman için örnek veri sağlamak amacıyla ortamına rastgele bir durum state = torch.rand(8) ile yüklenmiştir.

Bu egzersiz

Python ile Deep Reinforcement Learning

kursunun bir parçasıdır

Kursu Görüntüle

Egzersiz talimatları

Argüman olarak verilen durumda her eyleme karşılık gelen Q-değerlerini hesapla.
En yüksek Q-değerine sahip eylemin indeksini elde et.

Uygulamalı interaktif egzersiz

Bu örnek kodu tamamlayarak bu egzersizi bitirin.

def select_action(q_network, state):
    # Calculate the Q-values
    q_values = ____
    print("Q-values:", [round(x, 2) for x in q_values.tolist()])
    # Obtain the action index with highest Q-value
    action = torch.____.item()
    print(f"Action selected: {action}, with q-value {q_values[action]:.2f}")
    return action

select_action(q_network, state)

Kodu Düzenle ve Çalıştır

Bu egzersiz

Python ile Deep Reinforcement Learning

kursunun bir parçasıdır

AvançadoNível de habilidade

4.8+

Kursa Ücretsiz Başlayın

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

Exercise 1: Derin pekiştirmeli öğrenmeye giriş Exercise 2: Ortam ve sinir ağı kurulumu Exercise 3: DRL eğitim döngüsü Exercise 4: Deep Q öğrenmeye giriş Exercise 5: Deep learning ve DQN Exercise 6: Q-Ağı mimarisi Exercise 7: Q-Ağını Örneklendirme Exercise 8: Temel DQN algoritması Exercise 9: Temel DQN eylem seçimi

Geçerli Egzersiz

Exercise 10: Temel DQN kayıp fonksiyonu Exercise 11: Temel DQN'i eğitme

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: Introduction to policy gradient Exercise 2: The policy network architecture Exercise 3: Working with discrete distributions Exercise 4: Policy gradient and REINFORCE Exercise 5: Action selection in REINFORCE Exercise 6: Training the REINFORCE algorithm Exercise 7: Advantage Actor Critic Exercise 8: Critic network Exercise 9: Actor Critic loss calculations Exercise 10: Training the A2C algorithm

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!