AI and Machine Learning for Games

Take advantage of artificial intelligence, machine learning, and deep learning to build, run, and grow games

Introduction to AI/ML in Games

Gearbox Software and MMOS use machine learning to create minigame that helps advance scientific research

Solutions for every stage of the ML adoption journey

AI services for games
Improve player experiences with ready-made intelligence for applications and workflows. Take advantage of Amazon's ML services such as Amazon SageMaker, Amazon Rekognition, and more to protect players from toxic behavior, remove language barriers, improve accessibility, and personalize discovery
No/Low-code ML for game analytics and BI
AWS has made AI and low-code ML tools available for analytics and business intelligence teams. Use no-code ML tools like Amazon SageMaker Canvas, low-code ML tools built into AWS databases, or AutoML, to generate player predictions for LTV, propensity to churn, or propensity to purchase
Reinforcement and deep learning for games
For those ready to build production tools for content creation and testing, or player facing models utilizing reinforcement and deep learning to power dynamic stories, environments, and NPCs, AWS has the training programs, tools, and proprietary ML silicone you need to succeed

Custom-Built AI and ML solutions for games

Content monitoring

Amazon Rekognition enables image and video moderation automation, to proactively detect inappropriate, unwanted, or offensive User Generated Content (UGC) and grow a safe community

Learn more »
AI Agents for testing

Use Amazon Sagemaker to harness the power of Reinforcement Learning (RL) to tackle a wide range of challenges in games, like automated testing during build

Learn more »

AWS services

Analyze millions of images and videos within minutes to keep communities safe and reduce the volume of user generated content teams needs to manually review

Learn more »

Train Amazon Translate with games Translation Memory and Glossery for improved multilingual communication with global staff and players

Lear more »

SageMaker Canvas provides a visual point-and-click low/no-code tool analytics teams can use to generate player behaviour insights, LTV and Churn predictors with ML

Learn more »

Customer stories

See what our customers are achieving with AI&ML for Games on AWS.

Rovio

Rovio Teaches Angry Birds to Fly In the Cloud Using Machine Learning on AWS

With 4 billion analytic events captured per day, Rovio uses machine learning to predict and deliver the perfect level of fun for players. With AWS, Rovio can power its reinforcement learning to predict the difficulty of game levels faster.

Watch the presentation »
How Rovio teaches Angry Birds to fly in the cloud using ML
Gearbox and MMOS Use AWS to Create Minigame That Helps Scientific Research
Gearbox Entertainment

Gearbox and MMOS Use AWS to Create Minigame That Helps Scientific Research

Gearbox Software and MMOS use machine learning to create minigame that helps advance scientific research.

Read the case study »

MYTONA Finds AWS Changes the Game
MYTONA

MYTONA Finds AWS Changes the Game

MYTONA analyzes thousands of games reviews with Amazon SageMaker to sort and classify comments. It also runs daily Amazon ECS tasks to collect and pre-process data and to label new reviews. This provides feedback about games in near-real time.

Read the case study »

Watch the video »

How CAPCOM builds fun games fast with containers, data, and ML
Capcom

How CAPCOM builds fun games fast with containers, data, and ML

By using reinforcement learning on AWS, CAPCOM was able to reduce the burden on skilled workers to create well balanced levels at high velocity. 

Watch the presentation »

Voodoo: Perform Recommendations Using Machine Learning
VooDoo

Voodoo: Perform Recommendations Using Machine Learning

Voodoo used Amazon SageMaker to build, train, and deploy its machine learning inferences in production and improved recommendations for its players.

Watch the video »

Get started with AWS AI and ML

Detecting fraud with ML

Detect fraud in games using machine learning

Learn how to get fraud detection using ML up and running to train and run machine learning models that help detect in-game fraud

Read the blog »

Automate game leveling with reinforcement learning

Automate game leveling with reinforcement learning

Learn how to automate game leveling using reinforcement learning with Amazon SageMaker

Take the workshop »

Detect anomalies in games

Detect anomalies in games

Use Amazon Lookout for Metrics and the Game Analytics Pipeline Solution to find the "that's interesting" in analytics data. Get alerted to the unusual; a spike in crafting, a drop in chat traffic, or too many hits to the player authentication API

Take the workshop »

Up your game: Increase player retention with ML-powered matchmaking using Amazon Aurora ML and Amazon SageMaker

Up your game: Increase player retention with ML-powered matchmaking using Amazon Aurora ML and Amazon SageMaker

In this post, we demonstrate how a game publisher can adapt a player matchmaking system powered by Aurora to increase player retention using a real-time ML-based matchmaking model trained by Amazon SageMaker Autopilot.

Read the blog »

Apply profanity masking in Amazon Translate

Apply profanity masking in Amazon Translate

Learn how to mask profane words and phrases with a grawlix string (“?$#@$”) when using Amazon Translate for player-to-player multilingual chat in game

Read the blog »

Innovate with key industry partners

Discover purpose-built AWS for Games solutions and services from an extensive network of industry-leading AWS Partners who have demonstrated technical expertise and customer success in building solutions on AWS.

Spectrum Labs, Inc.

AI-powered content moderation

Guardian for Games, detect and stop harmful behaviors to optimize the player experience and grow your community.

Spectrum Labs, Inc. APN page »

Start the ML journey

Machine learning is the new technology frontier for games. Amazon is committed to helping game developers and game students master this technology and build amazing experiences with it.

Machine Learning University

Machine Learning University (MLU) provides anybody, anywhere, at any time access to the same machine learning courses used to train Amazon’s own developers on machine learning. With MLU, all developers can learn how to use machine learning with the learn-at-your-own-pace MLU Accelerator learning series.

Learn more about ML University »

Free Udacity course for AWS DeepRacer

Learn how to train a real life autonomous vehicle with Reinforcement Learning (RL) in this free 2 week Udacity course sponsored by AWS. Then test new skills by joining the DeepRacer Leage and win big prizes. 

Take the free course »

Amazon SageMaker Studio Lab (Preview)

Amazon SageMaker Studio Lab is a free machine learning (ML) development environment that provides the compute, storage (up to 15GB), and security—all at no cost—for anyone to learn and experiment with ML. Get started with a valid email address—no need to configure infrastructure or manage identity and access or even sign up for an AWS account.

Explore SageMaker Studio Lab »

Get your AWS Machine Learning Certification with A Cloud Guru

A Cloud Guru offers on-demand cloud education for all levels, including certification paths, hands-on labs, weekly episodes, and deep-dive courses that provide your teams with the skills they need to deliver results. Visit ACG at acloud.guru to learn more, or purchase a membership for teams directly from the AWS Marketplace.