This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
"""Script to illustrate usage of tf.estimator.Estimator in TF v1.3""" | |
import tensorflow as tf | |
from tensorflow.examples.tutorials.mnist import input_data as mnist_data | |
from tensorflow.contrib import slim | |
from tensorflow.contrib.learn import ModeKeys | |
from tensorflow.contrib.learn import learn_runner | |
# Show debugging output |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
"""A generic module to read data.""" | |
import numpy | |
import collections | |
from tensorflow.python.framework import dtypes | |
class DataSet(object): | |
"""Dataset class object.""" | |
def __init__(self, |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" 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 |