Rasio probabilitas yang di-klip

Sekarang Anda akan mengimplementasikan rasio probabilitas yang di-klip, sebuah komponen penting dari fungsi objektif PPO.

Sebagai referensi, rasio probabilitas didefinisikan sebagai: $$\frac{\pi_\theta(a_t|s_t)}{\pi_{\theta_{old}}(a_t|s_t)}$$

Dan rasio probabilitas yang di-klip adalah: \(\mathrm{clip}(r_t(\theta), 1-\varepsilon, 1+\varepsilon)\).

Latihan ini adalah bagian dari kursus

Deep Reinforcement Learning dengan Python

Petunjuk latihan

Peroleh probabilitas aksi prob dari action_log_prob, dan prob_old dari action_log_prob_old.
Lepaskan log probabilitas aksi lama dari grafik komputasi gradien torch.
Hitung rasio probabilitas.
Lakukan clipping pada surrogate objective.

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

log_prob = torch.tensor(.5).log()
log_prob_old = torch.tensor(.4).log()

def calculate_ratios(action_log_prob, action_log_prob_old, epsilon):
    # Obtain prob and prob_old
    prob = ____
    prob_old = ____
    # Detach the old action log prob
    prob_old_detached = ____.____()
    # Calculate the probability ratio
    ratio = ____ / ____
    # Apply clipping
    clipped_ratio = torch.____(ratio, ____, ____)
    print(f"+{'-'*29}+\n|         Ratio: {str(ratio)} |\n| Clipped ratio: {str(clipped_ratio)} |\n+{'-'*29}+\n")
    return (ratio, clipped_ratio)

_ = calculate_ratios(log_prob, log_prob_old, epsilon=.2)

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: 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: Optimisasi kebijakan proksimal Exercise 2: Rasio probabilitas yang di-klip

Latihan Saat Ini

Exercise 3: Fungsi objektif surrogate terpangkas (clipped)Exercise 4: Bonus entropi dan PPO Exercise 5: Ruang bermain entropi Exercise 6: Melatih algoritma PPO Exercise 7: Pembaruan batch dalam policy gradient Exercise 8: Minibatch dan DRL Exercise 9: A2C dengan pembaruan batch Exercise 10: Optimisasi hyperparameter dengan Optuna Exercise 11: Hyperparameter atau bukan?Exercise 12: Praktik langsung dengan Optuna Exercise 13: Selamat!