spinup/exercises/tf1/problem_set_1_solutions/exercise1_2_soln.py

import tensorflow as tf
import numpy as np


EPS = 1e-8

def mlp(x, hidden_sizes=(32,), activation=tf.tanh, output_activation=None):
    for h in hidden_sizes[:-1]:
        x = tf.layers.dense(x, units=h, activation=activation)
    return tf.layers.dense(x, units=hidden_sizes[-1], activation=output_activation)

def gaussian_likelihood(x, mu, log_std):
    pre_sum = -0.5 * (((x-mu)/(tf.exp(log_std)+EPS))**2 + 2*log_std + np.log(2*np.pi))
    return tf.reduce_sum(pre_sum, axis=1)

def mlp_gaussian_policy(x, a, hidden_sizes, activation, output_activation, action_space):
    act_dim = a.shape.as_list()[-1]
    mu = mlp(x, list(hidden_sizes)+[act_dim], activation, output_activation)
    log_std = tf.get_variable(name='log_std', initializer=-0.5*np.ones(act_dim, dtype=np.float32))
    std = tf.exp(log_std)
    pi = mu + tf.random_normal(tf.shape(mu)) * std
    logp = gaussian_likelihood(a, mu, log_std)
    logp_pi = gaussian_likelihood(pi, mu, log_std)
    return pi, logp, logp_pi