karpathy

""" 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

joaqo

// clang -O3 -march=native deleteme.c -o del_c

#include <stdio.h>
#include <time.h>
 
int main () {

	clock_t start, end;
	double cpu_time_used;
    int n[ 3000 ];