buffer.py

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

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

class Experience:
    def __init__(self, state, action, reward, next_state, done):
        self.state = state
        self.action = action
        self.reward = reward
        self.next_state = next_state
        self.done = done

class ReplayBuffer:
    
    def __init__(self, action_size, buffer_size, batch_size):
        self.action_size = action_size
        self.batch_size = batch_size
        self.memory = deque(maxlen=buffer_size)
        
    
    def sample(self, batch_size) -> tuple:
        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])).float().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 add(self, state, action, reward, next_state, done):
        experience = Experience(state, action, reward, next_state, done)
        self.memory.append(experience)

    def __len__(self):
        return len(self.memory)