How to train a tfjs model to play breakout game

-
Description

This is an artificial intelligence mechine learning practical experiment documentary on training an artificial intelligence neural network to play breakout game in the browser powered by tensorflow tfjs for JavaScript.

Introduction

 To understand how things will work breakout is a game which is alot more like ping pong your objective is to make sure the ball never goes by the puck in other words the player's puck should hit the ball before it heads into the lower bond of the screen.

Second objective 

Second objective is to make the ball destroy blocks by projecting it into the disired direction.

Normally this is not very important because the ball would normally iterate each and every corner on its own without trouble

Persudo code

 below is how this system works
// start initialization
// create model
// end initialization
// start update loop
async predict(should i move left or right). On resolve {set linear velocity}
if(ball crashed) {diagnose errors and generate reinforced training data effectively pushing it into the training samples}
// end update loop

Artificial intelligence model structuring

 Breakout artificial intelligence model is using a tensorflow sequential model.

First hidden layer 

First hidden layer of the model has four inputs using sigmoid activation function giving out eight output units.
Training data is in form [0, 0, 0, 0]
[[vector puck position] + [vector ball position]]
      
Second output layer

Second layer has 8 inputs coming from the previous hidden layer activation is done using sigmoid and output is given as 2 units.
Output is in form of two values rounded off to the nearest integer
[0, 0] [left, right]

Compiling the model

compiling is done using meanSquaredError loss function and adam optimizer with a learning rate of 0.1

References and citations

 "I've published the experiment in a repo on github "https://github.com/swashvirus/neuralBreakOut/" ,

🐣 "for the live demonstration here "https://swashvirus.github.io/neuralBreakOut/index.html"  ,

"Using TensorFlow.js to Automate the Chrome Dinosaur Game (part 1)"

Comments

Post a Comment

Popular posts from this blog

What is 'this.' keyword in JavaScript

-
In JavaScript 'this' is an object and a reference to the current object that is used to get and to set properties of the current object. Take for instance within a function; const func = function (name){     this.name = name } func.name instance property name is set to that of the first argument; const inst = new func('duke') inst.name // returns duke You can as well extend func to set name using 'this'; func.prototype.set = function(name){     this.name = name } Running the previous instance with this set method; inst.set('John') // returns John
Read more

How to iterate array elements using 'for loop' in JavaScript

-
JavaScript arrays are similar to arrays in c and in c like programming languages such as php among others In JavaScript arrays are simply collections of elements for instance Objects Numbers or other Arrays Declaring an array An array may be declared using the array constructor for instance const array = new Array() or as const array = [] Iterating an array using 'for' loop This is the implest and most common method to iterate an array is by using the 'for loop' am sure you're familiar with the syntax. take for Instance you want to iterate an array of integers and print each one of them. var ints = [1, 2, 3, 4] To iterate ints using for loop. for (var i = 0; i < ints.length; i++){         console.log(ints[i]) } // output will be // 1 // 2 // 3 // 4 In between the parentheses they are three procedures in three segments separated by colons first segment declares var i an index which gets incriminated in the third segment as long as it's less
Read more