Experience replay buffer

You will now create the data structure to support Experience Replay, which will enable your agent to learn much more efficiently.

This replay buffer should support two operations:

Storing experiences in its memory for future sampling.
"Replaying" a randomly sampled batch of past experiences from its memory.

As the data sampled from the replay buffer will be used to feed into a neural network, the buffer should return torch Tensors for convenience.

The torch and random modules and the deque class have been imported into your exercise environment.

This exercise is part of the course

Deep Reinforcement Learning in Python

Exercise instructions

Complete the push() method of ReplayBuffer by appending experience_tuple to the buffer memory.
In the sample() method, draw a random sample of size batch_size from self.memory.
Again in sample(), the sample is initially drawn as a list of tuples; ensure that it is transformed into a tuple of lists.
Transform actions_tensor into shape (batch_size, 1) instead of (batch_size).

Hands-on interactive exercise

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

class ReplayBuffer:
    def __init__(self, capacity):
        self.memory = deque([], maxlen=capacity)
    def push(self, state, action, reward, next_state, done):
        experience_tuple = (state, action, reward, next_state, done)
        # Append experience_tuple to the memory buffer
        self.memory.____    
    def __len__(self):
        return len(self.memory)
    def sample(self, batch_size):
        # Draw a random sample of size batch_size
        batch = ____(____, ____)
        # Transform batch into a tuple of lists
        states, actions, rewards, next_states, dones = ____
        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)
        # Ensure actions_tensor has shape (batch_size, 1)
        actions_tensor = torch.tensor(actions, dtype=torch.long).____
        return states_tensor, actions_tensor, rewards_tensor, next_states_tensor, dones_tensor

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

Current Exercise

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!