When reading binlog, I found one interesting code like below, just keep in mind here
#include <type_traits>
#include <cstdint>
#include <iostream>
struct Base{
int32_t i_data {123};
uint64_t u_data {123};
double d_data {123.0};
""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """ | |
import numpy as np | |
import cPickle as pickle | |
import gym | |
# hyperparameters | |
H = 200 # number of hidden layer neurons | |
batch_size = 10 # every how many episodes to do a param update? | |
learning_rate = 1e-4 | |
gamma = 0.99 # discount factor for reward |
#include <type_traits>
#include <cstdint>
#include <iostream>
struct Base{
int32_t i_data {123};
uint64_t u_data {123};
double d_data {123.0};