Reinforcement Learning

This Saturday at AiGameDev.com, there are quite a few insightful Smart Links from the blogosphere, in particular about upcoming games. Be sure to contact me if you have any news or tips for next week.
Remember there’s a mini-blog over at news.AiGameDev.com (RSS) with game AI news from the web as it happens.

Machine learning conceptually has many benefits for games, notably for reducing development times and creating AI that can adapt to the player. However, it is difficult to apply in the real-world! Transfer learning can help by improving the speed and quality of the learning. The idea is to use knowledge from previous experiences to […]

A new book recently came out explaining how to apply biologically inspired AI to games. It covers the classics in computational intelligence such as genetic algorithms, neural networks, artificial immune systems and particle swarm optimizations — not forgetting underrated techniques like reinforcement learning, independent component analysis, and radial basis functions.
I found out about […]

At a certain level, adaptation is a requirement for AI. If a game doesn’t have it, you end up living inside a movie you can’t change! In practice, all the traditional techniques (e.g. finite state machines, scripts) help developers implement adaptive behaviors, but things get tricky when you want to adapt to many […]

This is the third and final part of AiGameDev.com’s coverage of the research sessions relating to artificial intelligence at the GDC in Lyon. Be sure to read part 1 (about concurrent behaviors and Bayesian learning) and part 2 (about Embodied Communicational Agents).
This article in particular covers research into machine learning, and how it can […]

I’ll be in France on the 3rd and 4th of December at the Lyon GDC, giving a talk on using behavior trees for AI logic. There’s a surprisingly large number of game AI sessions generally, so it should be especially interesting for regular AiGameDev.com readers. Coverage will follow over the next couple of […]

This week’s Thursday Theory post on AiGameDev.com looks into applying reinforcement learning to bridge the gap between animation control and high-level AI logic. Specifically, this review covers autonomous characters that learn to move in a dynamic world, as developed by Leslie Ikemoto from the University of Berkeley.

This Saturday, there are five interesting Smart Links for you about game development and artificial intelligence! Feel free to contact me if you have any news or tips for next week.
Remember there’s a mini-blog over at news.AiGameDev.com (RSS) with game AI news from the web as it happens!

The Creatures game has played a very unique role in the history of games, selling over half a million units by incorporating many ideas from academic AI. It is touted as a breakthrough in artificial life, and incorporates both neural network algorithms and a form of artificial evolution to implement the Norns. This article reveals how this was done in practice.

Siggraph 2007 has been running for a few days now. Make sure you catch up on the three previous posts describing control innovations for character animation.
This paper is from the Texas A&M University Graphics and Animation Lab, and involves optimizing motions based on constraints using a statistical dynamic model. The innovation in this […]

Siggraph 2007 is underway today. See the previous two articles discussing this year’s innovations character animation technology.
Today’s research project is from the Carnegie Mellon Graphics department, and involves creating responsive characters from motion fragments. There are two main innovative ideas behind this paper:

Gathering traces from the gameplay helps model player movement.
Using reinforcement learning […]

Siggraph 2007 starts tomorrow. This post continues from yesterday’s review of character animation technology, discussing how this year’s innovations can be applied to game AI.
There’s another paper from University of Washington Animation Research Labs which presents a near-optimal continuous controller. There are two major innovations used:

A low-dimensional reinforcement learning algorithm to learn a […]