At this year's GDC AI Summit, we are holding a panel called, "AI Pre-Mortem: How to Approach Your AI Problems".

The official description of the session is:

AI for games can be a complicated area - particularly since there is often more than one approach to solving a problem. Sometimes, the best way to learn about how to approach AI problems is to hear veteran devs work through them. This panel features 4 AI developers who will take on a series of AI issues - from the mundane to the esoteric and challenging -- and talk through how they would think about and handle them. Some of the problems will be ones the panelists have encountered, some of them they will solicit from the community during the weeks leading up to GDC, and (if time permits and they are really feeling crazy) some will be from audience members right there during the session! They may not always come up with solutions, but will certainly try to think through the problem!

The panel is staffed by a number of creative, long-time AI devs from around the industry representing over 40 years of AI programming experience. Specifically, they are:

• Michael Dawe | Lead Software Engineer, GSN Games
• Rez Graham | Senior AI Programmer, Independent
• Brian Schwab | Lead AI/Gameplay Programmer, Magic Leap
• Damian Isla | Co-Founder / Tech, The Molasses Flood

I will be moderating -- often playing the role of designer asking, challenging, and providing the occasional twist just to keep things... interesting.

As mentioned, we are asking for ideas of interesting topics for the panelists to discuss. Due to time constraints, we will only be spending between 5 and 10 minutes on each topic so they can't be enormously complex. However, they also don't have to be beginner level issues. In fact, we would like to have a few head-scratchers for our panelists to address!

Whether you are attending GDC this year or not, we would like your input right here on this post. Post a short, direct, interesting game dev scenario -- particularly one that has stumped you for a while -- that you would like to learn how veteran AI programmers approach. We will then select some of the most compelling questions and pose them to the panelists during the session.

The plan is to ask GDC release this session for free on the GDC Vault. Even if you aren't able to attend, you may get your question answered!

So... whatcha got?

How an AI manages a large-scale battle in an RPG with many units and unit types. For example - When to retreat, which units should target others, group movement during the battle, consideration of reinforcements.

Maybe to abstract but I would love to get insight in how a professional would approach SRPG/TRPG AI namely how to get good team work rather than just separate entities all just doing there own thing.

Maybe to abstract but I would love to get insight in how a professional would approach SRPG/TRPG AI namely how to get good team work rather than just separate entities all just doing there own thing

That's actually a decent (and relatively common) one. Phrase it as something specific and I'm sure we can make it work.

I do have a question, and it's a big one, leaving your panel gasping for air

It's not game-related, but may be fun to ask anyway.

As you may know, RoboCup is a world-wide effort to create intelligent robots. http://www.robocup.org/about-robocup/

RoboCup@home is a part of it, where the aim is to build robots that act intelligently in real-time, interacting with humans in a house or public area. RoboCupRescue aims to build robots to find and help people in disaster locations.

A real-world environment is a highly confusing world. A house is a very dis-organized place. Tasks are very diverse, and perhaps not even known beforehand. Real-time interaction puts heavy constraints on what can be computed. In closer interaction (eg lifting someone out of bed, or digging someone out after a house collapsed), safety is a big concern.

What can the (game) AI community advice to make this work?

Way too broad and only loosely related to game dev. Remember, our audience is going to be game AI devs who are looking for solutions they can apply to their own projects. Perhaps by turning this on its head and simply asking something along the lines of handling cluttered, unknown, PCG, environments? Of course, we already have a session about that this year courtesy of Damian Isla and John Abercrombie.

http://schedule.gdconf.com/session/ai-for-generated-worlds

How an AI manages a large-scale battle in an RPG with many units and unit types. For example - When to retreat, which units should target others, group movement during the battle, consideration of reinforcements.

Spoilers.

Hmmm... this keeps coming up. Odd, that...

I don't know.how about:

How to get good team work out of individual entities in an SRPG/TRPG.

or

How professionals would approach SRPG/TRPG AI.

or

Putting the teamwork in Tactical game AI.

or

Tactical game AI a professional approach.

As you can tell I'm not particularly good at this, anyone want to help me come up with a title.