How have machine learning and AI influenced game design?
How have machine learning and AI influenced game design? originally appeared on Quora: the place to acquire and share knowledge, allowing people to learn from others and better understand the world.
Response from Travis Addair, Software Engineer, on Quora:
Games are more addictive today than ever, and a lot of that is thanks to machine learning.
When most people associate “AI” with “games,” they tend to think of “robots” or some other form of computer-controlled character (NPC).
But the reality is that machine learning is practically unused for such “AIs”. As I have discussed in other answers it’s just too expensive and doesn’t allow the degree of control required by the design team.
However, that’s not to say that machine learning is entirely absent from the game development process. In fact, it is used quite widely, but not in the Game itself, but in the way we design game systems.
let’s call it data-driven game design.
You see, game companies – especially big ones like Activision and EA – employ a lot of data scientists.
What are all these data scientists doing for the company? They do not directly play gamesrather, their role is to inform game design understanding player behavior.
How do they do this? Today, more and more games are moving their systems to the “backend” – the on the server side — where all the information about What the player does in the game and when whether they choose to play or not, the game can be tracked, recorded and analyzed.
This analysis can be simple – like a linear model used to correlate variables – but it becomes more and more very complex. As more and more data is tracked in greater quantity, more and more data science teams are turning to machine learning models like boosted gradient trees and deep neural networks.
To what end? Keeping players engaged in games, keeping them coming back for more.
This can be done at a macro level (looking at averages or user segmentations) or at a micro level (individuals).
What if you could predict when a player is about to stop playing your game? You could entice them back with a personalized bonus offer or in-game reward.
What if you knew the right frequency of rewards needed to keep a player interested and coming back each day? You can customize loot drops based on specific user preferences.
For better or worse, this is the direction the industry is heading, and we have machine learning to thank for it.
That question originally appeared on Quora – the place to gain and share knowledge, enabling people to learn from others and better understand the world. You can follow Quora on Twitter, Facebook and Google+. More questions: