Classical Snake Game in popup

Description

"Classical Snake Game in popup" - this is the best classic online game.

Dive into the childhood, remember how it was wonderful to spend the night playing the old school games.

There is an opinion that even our grandparents played this game. Classic games of 80-90х in free access.

Play online, nostalgic!

== How to play ==

Aside from the fact that it was the only game available on my cell phone at the time, I was really good at Snake. I still occasionally play it on my smartphone, but I've never been able to duplicate the same level of achievement as I once did.

What made Snake so awesome was its simplicity; all you needed was a monochrome phone, a few pixels, and rudimentary controls that were performed by pressing the number pad. If you're fortunate enough, you may be able to find that old Nokia phone from storage and relive the fun, but for everyone else, take a look at Snake '97 from developer dsd 164.

Snake '97 isn't some revolutionary game that you've never played. Rather, it's a classic game that you've probably played a million times on the toilet. But what separates Snake '97 is its degree of nostalgia, complete with a dot-matrix display, monotone sounds, and retro-looking cell phone overlays complete with number-pad controls.

The game is pretty self-explanatory. Your objective, as the snake, is to eat the square and continue growing. If you want to switch the overlay to something more recognizable, simply tap the display. You'll have speed, volume, and overlay options.

Hopefully the familiar layout facilitates a high score. Let us know what you thought of Snake '97 in the comments below, or just remind us of your favorite classic cell phone game.

Today I’m going to talk about a small practical example of using neural networks — training one to play a snake game.

This article is for beginners, so if you are good at machine learning you will not find something interesting for you. It would be great if you know something about machine learning, neural networks, and TensorFlow but there is no problem otherwise.

And finally, obviously, there are better approaches to write a logic for a snake game but let’s pretend that it is a real task and we need to solve it this way.

Part 0: The game
Firstly we need to write a game itself. It will have a 20x20 field, a snake of 3 pieces at the start, one randomly generated apple at each moment in time and API to use with our network. You can find a code of the game here.


Now let’s start with a neural network.

Part 1: Survive
Features
To make the snake “smart” we need to give some knowledge to it — we need to create features to teach it. Always try to choose features which will be most useful. If you add not enough features, a network will not get enough information to be good. From the other side, if there are too many features. it will be hard for a network to decide which are more important and learning will be longer.

At the first step, we will learn the snake how to survive and will not think about apples. To choose a right direction it should know if there are any obstacles around it. Considering these obstacles and suggested direction the network will decide is it a good action or not.

So on the input of our neural network we will give an array of 4 numbers:

Is there an obstacle to the left of the snake (1 — yes, 0 — no)
Is there an obstacle in front of the snake (1 — yes, 0 — no)
Is there an obstacle to the right of the snake (1 — yes, 0 — no)
Suggested direction (-1 — left, 0 — forward, 1 — right)
And as the output we want to receive a decision. 1 — we should go in the selected direction, 0 — we should choose another one.