Source code for algorithms.RL_Algorithm.optimizers.utils.math

import torch
import math


[docs]def normal_entropy(std):
    '''

    :param std: std value
    :return: calculate normal distribution entropy
    '''
    var = std.pow(2)
    entropy = 0.5 + 0.5 * torch.log(2 * var * math.pi)
    return entropy.sum(1, keepdim=True)


[docs]def normal_log_density(x, mean, log_std, std):
    '''

    :param x: x var
    :param mean: mean for the normal distribution
    :param log_std: log std
    :param std: std
    :return: log density of x var given the distribution
    '''
    var = std.pow(2)
    log_density = -(x - mean).pow(2) / (2 * var) - 0.5 * math.log(2 * math.pi) - log_std
    return log_density.sum(1, keepdim=True)