338 Game AI Programming Articles and Counting...
We help you find expert articles on commercial game AI development and other game programming topics.
Since many of these articles are published in books, this is the only site that helps you find them.
© 2012 Steve Rabin
Principal Software Engineer, Nintendo of America Inc.
Instructor, DigiPen Institute of Technology
ALERT: AI Game Programming Wisdom series is going OUT OF PRINT
Used copies of AI Game Programming Wisdom 4 are selling for $440.00 on Amazon. There are a couple new copies of the first volume from Amazon resellers at a reasonable price ($54.73).
Volumes 2 and 3 are still available, but since new books won't be printed, they will soon be just as scarce.
The whole series will soon be out of print - get your copies
$54.73 (8 new books left from resellers) AI Game Programming Wisdom 1
$39.96 (43% off) AI Game Programming Wisdom 2
$39.96 (43% off) AI Game Programming Wisdom 3
$440.00 (USED PRICE - out of print premium) AI Game Programming Wisdom 4
before they are gone:
Please don't contact me about AI Game Programming Wisdom 4 books. I don't have any to offer.
Call For Proposals:
After a 5 year break, there is going to be a new AI Wisdom book and you can be a part of it! At GDC 2012, I (Steve Rabin) hatched a plan that just might be crazy enough to work... I wanted to make an AI Wisdom book that would one day be FREE, yet have a professional book publisher perform their magic and produce a real physical book that will appear in bookstores, thus being a trophy and resume piece for each author.
Here's the bargain: Everyone involved (authors and editors) receives NO ROYALTIES (book royalties have always been very low and each author was lucky to a get $36 check every now and then). Well, no royalties is great for the book publisher, but what do the authors get in return?
Here's what I negotiated: After TWO YEARS, the entire book will be put on the web for FREE, FOREVER. Instead of reaching an audience of just 1500 to 3000 (the number of books typically printed), the articles will be available to be read, used, and referenced by 10,000 to 100,000 people over the next 10, 20, 50, 100 years. Articles in this new book will be extremely important and will have an impact for many, many years to come. YOU WANT TO BE A PART OF THIS BOOK!
Book publisher AK Peters (of the GPU Pro series) and editor Steve Rabin are looking for game developers to share their wisdom in this brand new volume in the style of the AI Game Programming Wisdom series. Anything that an AI game programmer would typically deal with is fair game, including pathfinding, animation control, scripting, learning, and various decision-making techniques. Selected authors will have several months to write and receive 3 free books. Proposals for 8-20 page articles are now being accepted until May 21st.
Submitting a Proposal - Follow these steps:
Collected Wisdom of Game AI Professionals (deadline May 21st, 2012)
- Prove that you can follow directions by including each of the following. Experience shows that people who include all items are more reliable and dependable, and thus are more likely to be chosen to write for the book.
- E-mail your proposal to firstname.lastname@example.org
- Make the subject of the e-mail your proposed article title.
- Write at least two detailed paragraphs explaining your topic. More details = better chance of acceptance. We like overachievers.
- Was the technique used in a game? Which game? Released or unreleased?
- Will you include a demo or source code with your article? (this will increase your chances of being chosen)
- Estimate the number of pages. We're looking for 8-20 pages per article (figures take 1/2 page each).
- Describe any previous writing experience.
- Describe your experience in the game industry and/or academic degrees.
- Include all contact information in case we have questions (email, phone #)
- Submit only one proposal per e-mail.
Note: Please submit several different proposals to increase your chances of being chosen.
Ideas for Proposals
- May 21st: Deadline for Proposals
- May 31st: Proposals chosen
- May 31st - July 15th: Authors write articles / demos
- July 15th - August 1st: Peer review
- August 1st - Sept 1st: Editing, revisions
- Sept 1st - Oct 1st: Final editing
- March 2013 (GDC): Book is published
Sections we are considering for the book:
- Since this is going to be an important "reboot" of the AI Wisdom series, I want to see 3 types of articles: (30%) Foundational articles for best practices on a particular subject, (60%) New innovative techniques proven in shipped games, and (10%) Forward looking techniques that might not have been tested in shipped games.
- First look at articles in past AI Wisdom books: AI Wisdom, AI Wisdom 2, AI Wisdom 3, AI Wisdom 4.
- You can follow-up or combine previous AI Wisdom articles, but it must be up-to-date and have some new information.
- Think about what AI systems you've developed that you were proud of. Are there any insights or algorithms that could help others?
- Did you learn the hard way how to correctly architect an AI for a particular genre (like football, RTS, or racing)? Could you explain a framework that worked well?
- Did you figure out a simple system or algorithm that appeared to have much more intelligence than it actually had?
- Do you have a horror story or lessons learned to share, like Mark Brockington's article "How Not to Write a Scripting Language"?
- Can you describe academic research that can be applied to practical game development?
- Do you have a small code base that you'd like to share (like Michael Zarozinski's "Free Fuzzy Logic Library" in the first AI Wisdom)?
- Do you have any wisdom gleaned from your last project that you'd like to share?
- Can you analyze and compare methods for a specific technique (like the article "The Ultimate Guide to FSMs in Games" in AI Wisdom2)?
- Do you have a collection of wisdom for a particular aspect of AI game programming (like the article "Strategies for Optimizing AI" in GPG2)?
- Have you found a really good use for more exotic AI techniques like Neural Networks or Genetic Algorithms?
- Have you used a common AI technique in an unconventional way?
Compensation for Articles
- General Wisdom
- Movement and Pathfinding
- Tactics and Planning
- Genre Specific (FPS, RTS, Action, Sports, etc)
- Scripting and Dialogue
- Learning and Adaptation
- Authors will receive 3 free books.
- In exchange for no royalties, after 2 years the entire book will be put on the web for free. In addition, after 2 years each author can post their chapter on their personal website and/or their company's website (however the copyright is maintained by the publisher and the article can't be resold or republished).
- A good feeling and bragging rights when you see your work in a local bookstore, like Barnes and Noble, and used/referenced by game developers for years to come.
Join the AI Game Programmers Guild!
The AI Game Programmers Guild is a professional group for discussing game AI with peers in the game industry.
Founded in 2008, there are currently over 300 members.
It's free to join, but you must have shipped at least one game as an AI programmer.
Request a membership here.
The Challenge of Game AI in Next-Gen Games
(Excerpt from Preface of AI Game Programming Wisdom 3)
Steve Rabin, January 19th, 2006
With the Xbox 360 and PS3, the next generation of game consoles is upon us and the bar has been raised yet again. Consumer expectations are extremely high and players demand more than just prettier versions of last-gen games. After shelling out upwards of $500 for these new systems and games, players are looking for new experiences which are substantially beyond what they've enjoyed previously.
With these high expectations, there are two game AI challenges new to this next generation. The first is for the subtle visible behavior of agents to keep pace with the incredibly detailed, high-polygon models. The second is to create agents which provide more interesting and novel gameplay experiences for the player.
The first challenge is relatively straightforward to understand, but difficult to overcome in practice. Increasingly realistic agent models must be complemented with equally adept and detailed behavior. It is critical for agent behavior consisting of navigation, movements, gestures, blinking, gaze, mannerisms, dialogue, and facial expressions to match the visual quality of the agent. Carefully crafted intelligence is required to direct animation, attention, and intention in a seamless and convincing manner.
As we venture towards extremely realistic looking characters, we perhaps run the risk of falling into the Uncanny Valley. This concept was proposed by Masahiro Mori in 1970 to explain an uneasiness which humans feel towards robots as they approach humanness. Mori claimed as robots start to resemble humans, we feel more empathetic toward them. However, as they approach humanness, the little differences which aren't quite right become extremely disturbing and unnerving-making robots seem more like undead zombies than real people. For example, film critic Roger Ebert proposed the movie Final Fantasy: The Spirits Within might have been rejected by audiences because its slightly imperfect computer animated humans fell into the Uncanny Valley. While the existence of the Uncanny Valley is debatable and hasn't been proven, it is nevertheless prudent for game developers to be aware of the challenge. If you are attempting realism, you must nail it, lest it become distracting to the overall experience.
Unfortunately, matching the visual quality of agents with competent and realistic behavior is unlikely to result in games which are substantially more fun to play. While we must maintain the steady climb in realism, it won't result in making games noticeably more enjoyable-which is what players demand with this next generation of consoles.
The second challenge is where I throw down the gauntlet and challenge game AI to save the day. If increasing realism doesn't give next-gen games the requisite new feel, then something else must help achieve it. One answer is for game design and AI to work hand-in-hand toward creating completely new gameplay experiences. This is a huge challenge because it requires the game designer to understand what is possible with AI and to closely work with the AI programmer. Because this type of relationship is rare in game development, it's an area which has huge potential for many game genres.
If high-end graphics pull the player in visually and accurate physics make the player feel like the world is real, then AI has the power to engage the player mentally. We don't want the AI to necessarily outwit the player (which is relatively easy), rather we want the player to rationalize and internalize the intelligence of the AI and reason about how to overcome it. It's not a question of how to beat the player but a question of how we can design a game in which intelligent agents can be creatively manipulated and exploited by a crafty player.
Given these two challenges for next-gen games, there is much work to do in the future. We need to become better at simulating realistic human behavior and we need to creatively use AI to bring new experiences to players. Meeting both of these game AI challenges will help differentiate this new generation of games from the last.
Links to Other Special Pages
Video Game Programming