experience_replay.py

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


DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")


class ReplayBuffer:
    """Fixed-size experience buffer"""

    def __init__(self, config):
        """Initialize a ReplayBuffer object."""
        self.memory = deque(maxlen=config["buffer"]["size"])
        self.experience = namedtuple("Experience", field_names=["state", "action", "reward", "next_state", "done"])
        self.seed = random.seed(config["general"]["seed"])

    def add(self, state, action, reward, next_state, done):
        """Add a new experience to memory."""
        e = self.experience(state, action, reward, next_state, done)
        self.memory.append(e)

    def sample(self, batch_size):
        """Randomly sample a batch of experiences from memory."""
        experiences = random.sample(self.memory, k=batch_size)

        states = torch.from_numpy(np.vstack([e.state for e in experiences if e is not None])).float().to(DEVICE)
        actions = torch.from_numpy(np.vstack([e.action for e in experiences if e is not None])).long().to(DEVICE)
        rewards = torch.from_numpy(np.vstack([e.reward for e in experiences if e is not None])).float().to(DEVICE)
        next_states = torch.from_numpy(np.vstack([e.next_state for e in experiences if e is not None])).float().to(DEVICE)
        dones = torch.from_numpy(np.vstack([e.done for e in experiences if e is not None]).astype(np.uint8)).float().to(DEVICE)

        return states, actions, rewards, next_states, dones

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