replay_buffer.py

from collections import deque
import random
import torch
import numpy as np

class ReplayBuffer:
    """Fixed-size buffer to store experience tuples."""

    def __init__(self, action_size, buffer_size, batch_size, seed, device):
        """Initialize a ReplayBuffer object.

        Params
        ======
            action_size (int): dimension of each action
            buffer_size (int): maximum size of buffer
            batch_size (int): size of each training batch
            seed (int): random seed
        """
        self.action_size = action_size
        self.memory = deque(maxlen=buffer_size)  
        self.batch_size = batch_size
        self.seed = random.seed(seed)
        self.device = device
    
    def add(self, state, action, reward, next_state, done):
        """Add a new experience to memory."""
        self.memory.append((state, action, reward, next_state, done))
    
    def sample(self):
        """Randomly sample a batch of experiences from memory."""
        experiences = random.sample(self.memory, k=self.batch_size)

        states = torch.from_numpy(np.vstack([e[0] for e in experiences if e is not None])).float().to(self.device)
        actions = torch.from_numpy(np.vstack([e[1] for e in experiences if e is not None])).long().to(self.device)
        rewards = torch.from_numpy(np.vstack([e[2] for e in experiences if e is not None])).float().to(self.device)
        next_states = torch.from_numpy(np.vstack([e[3] for e in experiences if e is not None])).float().to(self.device)
        dones = torch.from_numpy(np.vstack([e[4] for e in experiences if e is not None]).astype(np.uint8)).float().to(self.device)
  
        return (states, actions, rewards, next_states, dones)

    def __len__(self):
        """Return the current size of internal memory."""
        return len(self.memory)