Action selection in REINFORCE

Write the REINFORCE select_action function, which will be used by your REINFORCE agent to select an action at every step.

In DQN, the forward pass of the network returned Q-values; in REINFORCE, it returns action probabilities, from which an action can directly be sampled.

A policy network and a state have been loaded in your environment.

torch.distributions.Categorical has been imported as Categorical.

Cet exercice fait partie du cours

Deep Reinforcement Learning in Python

Afficher le cours

Instructions

Obtain the action probabilities as a torch tensor.
Obtain the torch Distribution corresponding to the action probabilities.
Sample an action from the distribution.

Exercice interactif pratique

Essayez cet exercice en complétant cet exemple de code.

def select_action(policy_network, state):
  # Obtain the action probabilities
  action_probs = ____
  print('Action probabilities:', action_probs)
  # Instantiate the action distribution
  action_dist = Categorical(____)
  # Sample an action from the distribution
  action = ____
  log_prob = action_dist.log_prob(action)
  return action.item(), log_prob.reshape(1)

state = torch.rand(8)
action, log_prob = select_action(policy_network, state)
print('Sampled action index:', action)
print(f'Log probability of sampled action: {log_prob.item():.2f}')

Modifier et exécuter le code

Cet exercice fait partie du cours

Deep Reinforcement Learning in Python

AvancéNiveau de compétence

4.8+

Commencer le cours gratuitement

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

Exercice en cours

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!