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

Jeraldy

 /**
 *
 * @author Deus Jeraldy
 * @Email: [email protected]
 * BSD License
 */

// np.java -> https://gist.github.com/Jeraldy/7d4262db0536d27906b1e397662512bc

import java.util.Arrays;

Jeraldy

package yourpackagename;

import java.io.IOException;
import java.nio.charset.Charset;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.HashMap;
import java.util.Map;
import java.util.logging.Level;
import java.util.logging.Logger;