Ayrık dağılımlarla çalışmak

Yakında stokastik politikalarla çalışacaksın: bir durumda ajan davranışını eylemler üzerindeki olasılık dağılımı olarak temsil eden politikalar.

PyTorch, ayrık dağılımları torch.distributions.Categorical sınıfıyla temsil edebilir; şimdi bununla denemeler yapacaksın.

Girdi olarak kullanılan sayıların, olasılıklarda olduğu gibi toplamının 1 olmasının aslında gerekli olmadığını göreceksin; otomatik olarak normalize edilirler.

Bu egzersiz

Python ile Deep Reinforcement Learning

kursunun bir parçasıdır

Kursu Görüntüle

Egzersiz talimatları

Kategorik olasılık dağılımını başlat.
Dağılımdan bir örnek al.
Olasılık olarak davranması için toplamı 1 olan 3 pozitif sayı belirt.
5 pozitif sayı belirt; Categorical bunları sessizce normalize ederek olasılıklara dönüştürecek.

Uygulamalı interaktif egzersiz

Bu örnek kodu tamamlayarak bu egzersizi bitirin.

from torch.distributions import Categorical

def sample_from_distribution(probs):
    print(f"\nInput: {probs}")
    probs = torch.tensor(probs, dtype=torch.float32)
    # Instantiate the categorical distribution
    dist = ____(probs)
    # Take one sample from the distribution
    sampled_index = ____
    print(f"Taking one sample: index {sampled_index}, with associated probability {dist.probs[sampled_index]:.2f}")

# Specify 3 positive numbers summing to 1
sample_from_distribution([.3, ____, ____])
# Specify 5 positive numbers that do not sum to 1
sample_from_distribution([2, ____, ____, ____, ____])

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: 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: Politika gradyanına giriş Exercise 2: Policy ağının mimarisi Exercise 3: Ayrık dağılımlarla çalışmak

Geçerli Egzersiz

Exercise 4: Policy gradient ve REINFORCE Exercise 5: REINFORCE'ta eylem seçimi Exercise 6: REINFORCE algoritmasını eğitme Exercise 7: Advantage Actor-Critic Exercise 8: Eleştirmen (Critic) ağı Exercise 9: Actor-Critic kayıp hesaplamaları Exercise 10: A2C algoritmasını eğitme

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!