IA on AI

Posts Tagged ‘Kevin Dill’

Both My GDC AI Summit Lectures on Utility Theory FREE on GDC Vault!

Wednesday, February 20th, 2013

It turns out that both of the GDC AI Summit lectures that I did with Kevin Dill are up on the GDC Vault for free now! Thanks to the folks at GDC for doing this — it’s a great honor to have my lectures selected as being among the free ones!

The links below will take you to the respective videos on the GDC Vault. If you are planning on attending the 2013 AI Summit at GDC, it will be helpful to watch these first. My lecture this year is a new structure for building utility-based systems using the mathematical concepts expressed in these prior lectures.

From 2010:


Improving AI Decision Modeling Through Utility Theory
Dave Mark, Intrinsic Algorithm
Kevin Dill, Lockheed Martin


The ‘if/then’ statement has been the workhorse of decision modeling longer than digital computing. Unfortunately, the harsh transition from yes to no often expresses itself through behavior in ways that are just as harsh. Utility theory has roots in areas such as psychology, economics, sociology, and classical game theory. By applying the science of utility theory with algorithmic techniques such as response curves, population distributions, and weighted randoms, we can improve the modeling of the underlying brain of our agents, broaden the potential decision space, and even manage edge cases that other decision systems stumble over.

From 2012:

gdc12_logoEmbracing the Dark Art of Mathematical Modeling in AI
Dave Mark, Intrinsic Algorithm
Kevin Dill, Lockheed Martin

Utility-based AI is a widely-used approach, particularly for games with deeper or more complex behavior. While new users may find utility functions complex and intimidating, experienced users see them as a natural and comfortable way to express behavior. In a follow-up of their 2010 lecture, Kevin Dill and Dave Mark will show how simple problems can be laid out quickly and easily using common design patterns. Additionally, they will show how complex situations can make use of utility functions to express more nuanced behavior. They will then walk through real-world examples, showing how they would be expressed in a utility-based architecture.

Dave Mark to speak at GameX Industry Summit

Friday, August 7th, 2009

I will be speaking along with Kevin Dill (Rockstar-New England) at the GameX Industry Summit in Philadelphia this October 24-25th. From the GameX site:

GameX Industry Summit is designed by industry professionals for industry professionals. It represents a deep and concerted production between the GameX production team and five IGDA chapters in New York, New Jersey, Boston, Baltimore and Philadelphia, bringing together the best and the brightest of the video game industry, right in the middle of the rapidly expanding East Coast game industry.

Our lecture will be as follows:

The Art of Game AI: Sculpting Behavior with Data, Formulas, and Finesse

Whether designer, producer, or programmer, the term “game AI” summons visions of cold, sterile code. Programmers that deal in AI may be more specific in their definition by listing technical tools such as state machines, search or pathfinding algorithms, behavior trees, or planning architectures. While there is value in selecting the proverbial “right tool for the job,” in very few cases will simply using a chosen tool yield the behaviors that make our characters come alive. The life-magic that we breathe into our agents must come from the subtlety of the numbers, formulas, and relationships between data that we plug into those tools.

This lecture will explore the challenges that are involved in constructing realistic behaviors, the mindset that one must adopt to accurately model these behaviors, and the techniques that can be used to construct them. We will show that many of the decision techniques can often be applied to a project regardless of the underlying logical infrastructure. The attendee will leave with a broad summary of how to approach the artistry of constructing artificial behaviors – and will likely have adopted the annoying habit of assigning values and formulas to everything they see around them.

I’m very much looking forward to sharing the stage with my friend and colleague – and the tech editor of my book, Behavioral Mathematics for Game AI (God help him!) It should be a fun and informative hour of material.