Source code for the Q-learning neural network

The following is the full code for the example shown previously:

import gym 
import numpy as np 
import random 
import tensorflow as tf 
import matplotlib.pyplot as plt 

#Define the FrozenLake enviroment 
env = gym.make('FrozenLake-v0') 

#Setup the TensorFlow placeholders and variabiles 
tf.reset_default_graph() 
inputs1 = tf.placeholder(shape=[1,16],dtype=tf.float32) 
W = tf.Variable(tf.random_uniform([16,4],0,0.01)) 
Qout = tf.matmul(inputs1,W) 
predict = tf.argmax(Qout,1) 
nextQ = tf.placeholder(shape=[1,4],dtype=tf.float32) 

#define the loss and optimization functions  
loss = tf.reduce_sum(tf.square(nextQ - Qout)) 
trainer = tf.train.GradientDescentOptimizer(learning_rate=0.1) 
updateModel = trainer.minimize(loss) 

#initilize the vabiables 
init = tf.global_variables_initializer() 

#prepare the q-learning parameters 
gamma = .99 
e = 0.1 
num_episodes = 6000 
jList = [] 
rList...