awjuliani

clear ; close all; clc
%Get input for three terms
prompt = 'First three letter term? ';
x1 = input(prompt, 's');
prompt = 'Second three letter term? ';
x2 = input(prompt, 's');
prompt = 'Four letter answer? ';
y = input(prompt, 's');

awjuliani

""" 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

awjuliani

import tensorflow as tf
import numpy as np
import tensorflow.contrib.slim as slim

total_layers = 25 #Specify how deep we want our network
units_between_stride = total_layers / 5

def highwayUnit(input_layer,i):
    with tf.variable_scope("highway_unit"+str(i)):
        H = slim.conv2d(input_layer,64,[3,3])

awjuliani

awjuliani

import tensorflow as tf
import numpy as np
import tensorflow.contrib.slim as slim

total_layers = 25 #Specify how deep we want our network
units_between_stride = total_layers / 5

def denseBlock(input_layer,i,j):
    with tf.variable_scope("dense_unit"+str(i)):
        nodes = []

awjuliani

import tensorflow as tf
import numpy as np
import tensorflow.contrib.slim as slim

total_layers = 25 #Specify how deep we want our network
units_between_stride = total_layers / 5

def resUnit(input_layer,i):
    with tf.variable_scope("res_unit"+str(i)):
        part1 = slim.batch_norm(input_layer,activation_fn=None)

awjuliani

class Worker():
      ....
      ....
      ....
      def work(self,max_episode_length,gamma,global_AC,sess,coord):
        episode_count = 0
        total_step_count = 0
        print "Starting worker " + str(self.number)
        with sess.as_default(), sess.graph.as_default():                 
            while not coord.should_stop():

awjuliani

# Copies one set of variables to another.
# Used to set worker network parameters to those of global network.
def update_target_graph(from_scope,to_scope):
    from_vars = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, from_scope)
    to_vars = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, to_scope)

    op_holder = []
    for from_var,to_var in zip(from_vars,to_vars):
        op_holder.append(to_var.assign(from_var))
    return op_holder

awjuliani

with tf.device("/cpu:0"): 
    master_network = AC_Network(s_size,a_size,'global',None) # Generate global network
    num_workers = multiprocessing.cpu_count() # Set workers ot number of available CPU threads
    workers = []
    # Create worker classes
    for i in range(num_workers):
        workers.append(Worker(DoomGame(),i,s_size,a_size,trainer,saver,model_path))

with tf.Session() as sess:
    coord = tf.train.Coordinator()

awjuliani