aabbas90

import numpy as np

class ReplayBuffer:
    def __init__(self, a = 1.0, b = 0.7):
        self.keys = []
        self.values = []
        self.a = a
        # b < 1.0 allows to sample near the max key more frequently.
        # This allows to sample more trajectories where optimization is difficult, 1.0 will do uniform distribution.
        self.b = b

aabbas90

# Adapted from https://github.com/cyang-kth/maximum-coverage-location

import numpy as np
from gurobipy import *
from numpy import random
from scipy.spatial import distance_matrix
import argparse

def mclp(points, sites, demands, B, radius):
    print('----- Configurations -----')