memory.py

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

class ReplayBuffer:

	def __init__(self, action_size, buffer_size, batch_size, seed):
		self.action_size = action_size
		self.memory = deque(maxlen=buffer_size)  
		self.batch_size = batch_size
		self.experience = namedtuple("Experience", field_names=["state", "action", "reward", "next_state",  "done"])
		self.seed = random.seed(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):
		experiences = random.sample(self.memory, k=self.batch_size)

		device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

		states = torch.from_numpy(np.array([e.state for e in experiences if e is not None])).float().to(device)
		actions = torch.from_numpy(np.array([e.action for e in experiences if e is not None])).float().to(device)
		rewards = torch.from_numpy(np.array([e.reward for e in experiences if e is not None])).float().to(device)
		next_states = torch.from_numpy(np.array([e.next_state for e in experiences if e is not None])).float().to(device)
		dones = torch.from_numpy(np.array([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 len(self.memory)