Sampling from the PER buffer

Before you can use the Prioritized Experience Buffer class to train your agent, you still need to implement the .sample() method. This method takes as argument the size of the sample you want to draw, and returns the sampled transitions as tensors, along with their indices in the memory buffer and their importance weight.

A buffer with capacity 10 has been pre-loaded in your environment for you to sample from.

This exercise is part of the course

Deep Reinforcement Learning in Python

Exercise instructions

Calculate the sampling probability associated with each transition.
Draw the indices corresponding to the transitions in the sample; np.random.choice(a, s, p=p) takes a sample of size s with replacement from the array a, based on probability array p.
Calculate the importance weight associated with each transition.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

def sample(self, batch_size):
    priorities = np.array(self.priorities)
    # Calculate the sampling probabilities
    probabilities = ____ / np.sum(____)
    # Draw the indices for the sample
    indices = np.random.choice(____)
    # Calculate the importance weights
    weights = (1 / (len(self.memory) * ____)) ** ____
    weights /= np.max(weights)
    states, actions, rewards, next_states, dones = zip(*[self.memory[idx] for idx in indices])
    weights = [weights[idx] for idx in indices]
    states_tensor = torch.tensor(states, dtype=torch.float32)
    rewards_tensor = torch.tensor(rewards, dtype=torch.float32)
    next_states_tensor = torch.tensor(next_states, dtype=torch.float32)
    dones_tensor = torch.tensor(dones, dtype=torch.float32)
    weights_tensor = torch.tensor(weights, dtype=torch.float32)
    actions_tensor = torch.tensor(actions, dtype=torch.long).unsqueeze(1)
    return (states_tensor, actions_tensor, rewards_tensor, next_states_tensor,
            dones_tensor, indices, weights_tensor)

PrioritizedReplayBuffer.sample = sample
print("Sampled transitions:\n", buffer.sample(3))

Edit and Run Code

This exercise is part of the course

Deep Reinforcement Learning in Python

AdvancedSkill Level

4.8+

Start Course for Free

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

Current Exercise

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!