Categories: Insights

How AI is changing game development

4 min read

Artificial intelligence is transforming many areas, but one of the most interesting and underrated is gaming. It’s not that surprising; after all, an AI last year beat the world’s top Go player, and it’s not a giant leap to see how artificial intelligence might be used in modern video gaming. However, things aren’t straightforward. This is because applying artificial intelligence to a video game is different from artificial intelligence applied to the development process of video game. Before we talk further about this, let’s first discuss artificial intelligence by itself.

What exactly is artificial intelligence? Artificial intelligence is, to put it simply, the ability of machines to learn and apply knowledge. Learning and applying knowledge is such a broad scope though. Being able to do simple math calculations is learning and applying arithmetic knowledge, but no one would call that capability artificial intelligence.

Artificial intelligence is a shifting field

Surprisingly, there is no definite scope for the kind of knowledge that artificial intelligence must have. It’s a moving goalpost, the scope is updated whenever a new breakthrough in the field of artificial intelligence has occurred. There is a saying in the artificial intelligence community that “AI is whatever hasn’t been done yet,” meaning that whenever an AI problem is solved and figured out, it no longer counts as artificial intelligence and will be branched out to its own field. This has happened to searching algorithm, path finding, optical character recognition, and so on.

 So, in short, we have a divide here. When experts are saying artificial intelligence, they usually mean the most cutting-edge part of artificial intelligence like neural networks or advanced voice recognition. Meanwhile, problems that are seen as solved, like path finding, are usually no longer being researched and not counted as artificial intelligence anymore.

And it’s also why all the advancement that has happened to artificial intelligence doesn’t really impact video games. Yes, video games have many, many applications of artificial intelligence, but most of those applications are limited to problems that have already been solved like path finding and decision making. Meanwhile, the latest artificial intelligence technique like machine learning doesn’t really have a place in video games.

Things are a bit different though for video game development. Even though video games themselves don’t use the latest and greatest artificial intelligence, their creation is still an engineering process that can be further aided with the advancement in AI. Do note that most of the artificial intelligence used for game development is still being explored and still in an experimental phase.

 There has been research done recently about using an intelligent agent to learn about level layout of a game and then using that trained agent to layout another level. Having an artificial intelligence handle the level creation aspect of a game development will definitely increase the development speed because level designers now can just tweak existing layout instead of starting from scratch.

Automation in game development

 Another aspect of video game development that already uses a lot of automation and can be aided further by artificial intelligence is quality assurance (QA). By having an artificial intelligence that can learn how to play the game will great assist developers when they need to check for bugs and other issues. But of course, artificial intelligence can only detect stuff that can be measured like bugs and crashes, and they won’t be able to see if the game is fun or not.

Using AI to improve game design

 Having an AI that can automatically play a video game isn’t only good for testing purposes, but it could also help improve game design. There was a mobile game studio that uses artificial intelligence to mimic human behavior so they can determine the difficulty of the game. By checking how the artificial intelligence performs on a certain level, designers can project how real players would perform on that level and adjust the difficulty properly.

 And that’s how AI is changing game development. Despite all the advancement, there is still plenty of work to be done for artificial intelligence to truly assist game developers in their work. That said, game development is one of those jobs that don’t need to worry about being replaced by robots, because more than anything, game development is a creative endeavor that only humans can do. Well, so far at least.


Raka Mahesa is a game developer at Chocoarts (http://chocoarts.com/) who is interested in digital technology in general. Outside of work, he enjoys working on his own projects, with Corridoom VR being his latest relesed gme.

Raka Mahesa

Share
Published by
Raka Mahesa

Recent Posts

Top life hacks for prepping for your IT certification exam

I remember deciding to pursue my first IT certification, the CompTIA A+. I had signed…

3 years ago

Learn Transformers for Natural Language Processing with Denis Rothman

Key takeaways The transformer architecture has proved to be revolutionary in outperforming the classical RNN…

3 years ago

Learning Essential Linux Commands for Navigating the Shell Effectively

Once we learn how to deploy an Ubuntu server, how to manage users, and how…

3 years ago

Clean Coding in Python with Mariano Anaya

Key-takeaways:   Clean code isn’t just a nice thing to have or a luxury in software projects; it's a necessity. If we…

3 years ago

Exploring Forms in Angular – types, benefits and differences   

While developing a web application, or setting dynamic pages and meta tags we need to deal with…

3 years ago

Gain Practical Expertise with the Latest Edition of Software Architecture with C# 9 and .NET 5

Software architecture is one of the most discussed topics in the software industry today, and…

3 years ago