Werken met discrete verdelingen

Je gaat straks werken met stochastische policies: policies die het gedrag van de agent in een gegeven staat weergeven als een kansverdeling over acties.

PyTorch kan discrete verdelingen representeren met de klasse torch.distributions.Categorical, waar je nu mee gaat experimenteren.

Je zult zien dat het niet nodig is dat de getallen die je als invoer gebruikt optellen tot 1, zoals kansen dat doen; ze worden automatisch genormaliseerd.

Deze oefening maakt deel uit van de cursus

Deep Reinforcement Learning in Python

Cursus bekijken

Oefeninstructies

Maak een instantie van de categorische kansverdeling.
Neem één steekproef uit de verdeling.
Geef 3 positieve getallen op die optellen tot 1 als kansen.
Geef 5 positieve getallen op; Categorical zal ze stilzwijgend normaliseren tot kansen.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

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, ____, ____, ____, ____])

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: 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: Introductie tot policy gradient Exercise 2: De architectuur van het policy-netwerk Exercise 3: Werken met discrete verdelingen

Huidige oefening

Exercise 4: Policy gradient en REINFORCE Exercise 5: Actieselectie in REINFORCE Exercise 6: De REINFORCE-algoritme trainen Exercise 7: Advantage Actor-Critic Exercise 8: Critic-netwerk Exercise 9: Actor-Critic: verliesberekeningen Exercise 10: Het A2C-algoritme trainen

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!