basic_buffer.py

from collections import deque
import random
import numpy as np

class BasicBuffer:

    def __init__(self, max_size):
        self.max_size = max_size
        self.buffer = deque(maxlen=max_size)

    def push(self, state, action, reward, next_state, target, done):
        experience = (state, action, np.array([reward]), next_state, target, done)
        self.buffer.append(experience)

    def sample(self, batch_size):
        state_batch = []
        action_batch = []
        reward_batch = []
        next_state_batch = []
        target_batch = []
        done_batch = []

        batch = random.sample(self.buffer, batch_size)

        for experience in batch:
            state, action, reward, next_state, target, done = experience
            state_batch.append(state[0])
            action_batch.append(action)
            reward_batch.append(reward)
            next_state_batch.append(next_state)
            target_batch.append(target)
            done_batch.append(done)

        return (state_batch, action_batch, reward_batch, next_state_batch, target_batch, done_batch)

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