Loop pelatihan DRL

Agar agen dapat berinteraksi dengan environment berulang kali, Anda perlu menyiapkan loop pelatihan.

Banyak algoritma DRL memiliki struktur inti yang sama:

Loop melalui episode
Loop melalui langkah di dalam tiap episode
Pada setiap langkah, pilih aksi, hitung loss, dan perbarui jaringan

Anda disediakan fungsi placeholder select_action() dan calculate_loss() agar kode dapat berjalan. Network dan optimizer yang didefinisikan dari latihan sebelumnya juga tersedia untuk Anda.

Latihan ini adalah bagian dari kursus

Deep Reinforcement Learning dengan Python

Petunjuk latihan

Pastikan loop luar (untuk episode) berjalan selama sepuluh episode.
Pastikan loop dalam (untuk langkah) berjalan hingga episode selesai.
Ambil aksi yang dipilih oleh select_action() di environment env.
Di akhir tiap iterasi loop dalam, perbarui state sebelum memulai langkah berikutnya.

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

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.")

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: Pengantar deep reinforcement learning Exercise 2: Penyiapan environment dan neural network Exercise 3: Loop pelatihan DRL

Latihan Saat Ini

Exercise 4: Pengantar deep Q learning Exercise 5: Deep learning dan DQN Exercise 6: Arsitektur Q-Network Exercise 7: Menginstansiasi Q-Network Exercise 8: Algoritma DQN dasar Exercise 9: Pemilihan aksi DQN dasar Exercise 10: Fungsi loss DQN sederhana Exercise 11: Melatih 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: 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!