import numpy as np
import torch


def dev0(a, b):
    a = a.detach().numpy()
    b = b.detach().numpy()
    with np.errstate(divide='ignore', invalid='ignore'):
        c = np.true_divide(a, b)
        c[~ np.isfinite(c)] = 0
    c = torch.from_numpy(c)
    return c


def soft_update(target, source, tau):
    for target_param, param in zip(target.parameters(), source.parameters()):
        target_param.data.copy_(target_param.data * (1.0 - tau) + param.data * tau)


def hard_update(target, source):
    for target_param, param in zip(target.parameters(), source.parameters()):
        target_param.data.copy_(param.data)


class DeepQNetwork: