Support NeoGAF

[IbizaPocholo]

EA Wants to Get Better at Predicting Players' Skill Levels

EA is applying for a patent utilizing deep learning technology to analyze player skills and provide more even match-ups across all of its games.

gamerant.com

EA has applied for a patent utilizing deep-learning technology to improve automated match-making for players across all of its games. Using a neural network to analyze player skill and match outcomes should result in more satisfying matches for players. Different EA titles have tried various approaches to solve the problem of online match-making, from utilizing the classic competitive Chess ELO system to the Engagement Optimized Match Making System which was designed to keep gamers playing for longer online sessions. Both of those methods utilized in the past have their drawbacks which will ideally not be present in a neural network powered deep learning system.

According to the patent filed by EA, its neural network will analyze players in a prospective pool by looking at the overall player statistics and then searching for players with the best estimated individual skill ratings to create the ideal match up. Estimated player score, such as their KDA (Kills, Deaths, and Assists) in a FPS title or goals scored in FIFA, will be calculated based off of prior match results and then calculate each individual player score to get an estimated rating for the team of players during a match. In practice the process will be similar to the terrain generating neural network EA also patented with millions of mathematical calculations taking place behind the scenes at the same time.

Within the patent application, EA claims that the neural network will take into account further variables, including how each player behaviors on specific maps or with individual players in a sports title. For example if a player usually plays Pathfinder in Apex Legends but changes and decides to play as Crypto for a match, the neural network will find other players with similar predicted match outcomes closer to their expected behavior as Crypto, which should result in a more balanced match up. Ideally matches made with the proposed neural network would eliminate the problem with smurfs Apex Legends for example.

------------------------------------------------------------------------------------------------------------------------------------------

EA Patent Uses Spatial Partitioning for Improved Graphics Rendering

Electronic Arts' latest patent promises a faster and more flexible graphics rendering technique the leverages spatial partitioning.

gamerant.com

Electronic Arts appears to be working on a new type of render technology that would use spatial partitioning to offset and reduce the gaming devices' hardware load. The popular game publisher and developer has submitted a great number of key patent listings over the course of 2022, with some of them having the potential to substantially improve EA's games across the board, though it goes without saying that it takes time for a patented solution to be fully developed.

Coming just a few months after EA patented its input delay compensation feature, the company is now seemingly looking at ways to revolutionize real-time graphics rendering by compartmentalizing the hardware's visualization load. Its latest patent submission leverages the method of spatial partitioning to divide the game world into disparate zones, each of which is subsequently easier to load and render in real-time since the hardware in question no longer needs to deal with the entire game world all at once. The description specifies that this would be accomplished through the use of dynamic reverse tree generation, letting the PC or console know what needs to be loaded at a given moment in time.

 

[ZoukGalaxy]

 

[[Sigma]]

 

[kikkis]

Isn't spatial partitions used by like tons of games by now.

 

[Elysion]

Yeah, that ‘partitioning’ thing sounds like something that games have been using since forever. I mean, ‘dividing the game world into zones’ sounds pretty mundane, unless I’m missing something?