Featured Highlights

Paper Bot: Automated Highlights from a Database of 474 Papers
Open Article April 16th, 2015

Paper Bot: Automated Highlights from a Database of 474 Papers

The @AiGameDev Twitter bot automatically posts interesting highlights from research papers gathered from recent CIG and AIIDE conferences. It uses some simple image-based techniques to find things to post, powered by Python and libraries such as scikit-image and scipy. Find out how it was done and look at some examples...

Crowd Animation Techniques and Tools from Visual Effects
Insider Broadcast April 30th, 2015

Crowd Animation Techniques and Tools from Visual Effects

This broadcast with Michaël Rouillé, CTO at Golaem, will explain the crowd simulation techniques and tools required to animate convincing crowds in many films, TV series and adverts. He'll also discuss how these ideas and tools can be applied within real-time simulations and games.

READ MORE »
LIVE in 1430420447
Deep Gabe: Machine Learning from Steam Data with Neural Networks
Premium Presentation March 17th, 2015

Deep Gabe: Machine Learning from Steam Data with Neural Networks

Over the past few years, deep learning has revolutionized the technology sector by providing significantly better results on classification or prediction problems that were previously impractical for machine learning. What are the benefit for game developers? What's the catch? This presentation is a practical introduction to deep neural networks, using millions of public player profiles and thousands of games ...

Latest Articles

Premium Coverage April 15th, 2015

Take-Aways and High-Level Analysis from GDC 2015

Take-Aways and High-Level Analysis from GDC 2015

This recording digs into most important ideas and techniques in Game AI from GDC last month, including the AI Summit, as well as big trends take-aways from the conference. You'll hear about the AI, animation and procedural generation in games such as Sunset Overdrive, Watch_Dogs, Galak-Z, and more.

Premium Tutorial April 4th, 2015

How To Train Your Neural Network: A Python Guide

How To Train Your Neural Network: A Python Guide

Using Python is one of the simplest ways to get started with deep learning and neural networks. This tutorial will show you how you can get up and running with PyLearn2 via a simple wrapper library, and the various issues and questions you need to be considering in practice to get things working efficiently and reliably.

Open Editorial December 31st, 2014

Games of the Year: The 2014 AiGameDev.com Awards ...

Games of the Year: The 2014 AiGameDev.com Awards for Game AI

Every year AiGameDev.com hosts the Awards for Game AI, shining the spotlight on the best releases of the past twelve months. There are six different awards, ranging from technology to design and of course overall game of the year.

Insider Masterclass Oct 7th, 2014

ACME Corporation’s Detailed Guide to Explosive ...

ACME Corporation’s Detailed Guide to Explosive Game AI Research

A masterclass for new research students in the field of Game AI. What's the state of the art in the various fields of applied AI in games, and how do you identify/approach research opportunities? In particular, you'll learn about Character Behavior, Intelligent Games, Design Tools, Hardware Devices and Game Analytics. Make sure you're at ...

Open Coverage August 12th, 2014

Monte-Carlo Tree Search in TOTAL WAR: ROME II's ...

Monte-Carlo Tree Search in TOTAL WAR: ROME II's Campaign AI

Monte-Carlo Tree Search is a powerful AI algorithm that was recently discovered and in the past years has found great success in board games. This year, MCTS finally hit the AAA games industry, specifically thanks to Creative Assembly's TOTAL WAR: ROME II. Find out more about the design motivations for using the algorithm, how it was ...

Insider Interview April 30th, 2013

The CTF Winners' Secrets

The CTF Winners' Secrets

Our Capture The Flag Competition over at AiSandbox.com saw a couple of fierce and exciting battles. We have asked our top scorers Alexander Shafranov, Traffic Jam, and Thomas Dupuis to share with us what they thought their commander is particularly good at. Here is what they have told us.


  • SpirOps AI
  • PathEngine
  • Havok