How Ubisoft Is Mainstreaming Machine Learning Into Game Development

Without a doubt, Game Development is one of the toughest jobs, and for several years, gaming companies have been trying to leverage the superpowers of machine learning (ML). However, game developers are wary of ML and its limited use in games.

The question that arises here is AI is already doing a great job in the field of game development, then why should one add machine learning in game development. Over the years, ML has helped many industries reach the height of success, and it has the ability to make a huge impact on the way video games are developed. ML would not only help in developing games but would also help in transforming the experience of gaming — whether it’s about characters, challenges, and content. Therefore, in order to stay relevant to the current trends in the market, game companies across the world are working day in and out to reap benefits ML.

Another big advantage of baking ML in game development is that unlike traditional video games where the characters are scripted, ML-based games will have the ability to learn for the player and act accordingly to the environment. So basically, ML-based games learn to react and respond more dynamically and more realistically to the player.


Sign up for your weekly dose of what's up in emerging technology.

The Challenge Ahead

In order to make machine learning go-to tech video games, developers need to have a learning agent that can learn from players. However, this is not something really easy — there lie challenges. The learning agent might have to learn from a human in order to act and respond more accurately, and to teach an ML system, one has to be really good at that video game.

That is not all, human-in-the-loop will also have to teach the ML system/learning agent other skills to make sure that it acts and responds not only to one kind of player but also to another type of players.

Download our Mobile App

Ubisoft Use Cases

While the rest of the world is thinking and planning to implement machine learning in game development, Montreal-based video game company Ubisoft has already played its cards to make use of machine learning.

Action-adventure video game published by Ubisoft in 2017, Assassin’s Creed Origins was inspired by the landscape and history of the Ptolemaic period of Ancient Egypt. And in order to make the game more realistic, Ubisoft used elements of history to build a world for its players.

Furthermore, Ubisoft used machine learning model in the game. However, there were challenges — to train the machine learning model that was used in the game to recognize hieroglyphics. Also, developing machine learning models was a challenge and was a very time-consuming process. And the Google Cloud Platform and Cloud AutoML was the answer to all their problems.

Also, bugs and complexities can cause a lot of issues when creating a high-end video game, and in order to cope with that, Ubisoft has built an AI assistance for its developers that uses machine learning to discover bugs before they make it into the final game code.

How does it work? Dubbed as Commit Assistance, the system has a different signature for a different type of codes. Every time code is presented to the AI assistance, the system analyses the code to see if any of the signature matches. As soon a match is found, the system notifies that it’s a bug.

As of now, that system is capable of spotting 6 out of 10 coding errors. Also, it raises a false alarm 30 per cent of the time, however, as it is mentioned before that it uses machine learning, the system over time, will be able to reduce that if more and more code is fed through the algorithm.

Moreover, this Assistance has gained so much popularity that even Mozilla today uses this machine learning platform to spot bugs on Firefox.


There is no doubt that machine learning has immense potential to transform any industry for the good. Challenges are always there in every industry and game development is no exception, however, talking about game development, Ubisoft’s significant steps seem to be doing the job already. And with more game companies getting involved in this venture of using ML in game dev, there is no doubt that the video game industry will soon experience a tremendous transformation.

Support independent technology journalism

Get exclusive, premium content, ads-free experience & more

Rs. 299/month

Subscribe now for a 7-day free trial

More Great AIM Stories

Harshajit Sarmah
Harshajit is a writer / blogger / vlogger. A passionate music lover whose talents range from dance to video making to cooking. Football runs in his blood. Like literally! He is also a self-proclaimed technician and likes repairing and fixing stuff. When he is not writing or making videos, you can find him reading books/blogs or watching videos that motivate him or teaches him new things.

AIM Upcoming Events

Early Bird Passes expire on 3rd Feb

Conference, in-person (Bangalore)
Rising 2023 | Women in Tech Conference
16-17th Mar, 2023

Conference, in-person (Bangalore)
Data Engineering Summit (DES) 2023
27-28th Apr, 2023

3 Ways to Join our Community

Telegram group

Discover special offers, top stories, upcoming events, and more.

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Subscribe to our Daily newsletter

Get our daily awesome stories & videos in your inbox

All you need to know about Graph Embeddings

Embeddings can be the subgroups of a group, similarly, in graph theory embedding of a graph can be considered as a representation of a graph on a surface, where points of that surface are made up of vertices and arcs are made up of edges