Het Q-netwerk instantiëren

Nu je de architectuur hebt gedefinieerd, kun je het daadwerkelijke netwerk instantiëren dat je agent gaat gebruiken, plus de optimizer. De Lunar Lander-omgeving heeft een toestandsruimte met dimensie 8 en een actieruimte met dimensie 4 (overeenkomend met 0: niets doen, 1: linker thruster, 2: hoofdmotor, 3: rechter thruster).

De klasse QNetwork uit de vorige oefening is voor je beschikbaar.

Deze oefening maakt deel uit van de cursus

Deep Reinforcement Learning in Python

Cursus bekijken

Oefeninstructies

Instantieer een Q-netwerk voor de Lunar Lander-omgeving.
Definieer de Adam-optimizer voor het neuraal netwerk met een leersnelheid van 0,0001.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

state_size = 8
action_size = 4
# Instantiate the Q Network
q_network = QNetwork(____, ____)
# Specify the optimizer learning rate
optimizer = optim.Adam(q_network.parameters(), ____)

print("Q-Network initialized as:\n", q_network)

Code bewerken en uitvoeren

Deze oefening maakt deel uit van de cursus

Deep Reinforcement Learning in Python

SkillTag.level.advancedSkillTag.label

4.8+

Begin de cursus gratis

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

Exercise 1: Introductie tot deep reinforcement learning Exercise 2: Omgeving en neuraal netwerk instellen Exercise 3: DRL-trainingslus Exercise 4: Introductie tot deep Q-learning Exercise 5: Deep learning en DQN Exercise 6: De Q-Network-architectuur Exercise 7: Het Q-netwerk instantiëren

Huidige oefening

Exercise 8: Het kale DQN-algoritme Exercise 9: Barebone DQN-actie-selectie Exercise 10: Barebone DQN-verliesfunctie Exercise 11: Een barebone DQN trainen

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!