Some people were complaining that the audio interview with the AI lead on Bioshock was either playing too fast or the applet itself was not loading. I have edited the original page to show a link to the actual audio file. Let me know if that is not working for you.
I have kinda entered a vortex of browsing through other people's GDC coverage - especially on the sessions that I could not attend. Note that I don't necessarily agree with everything that people have posted here - I'm just including them so people can have a broader picture. Here's a partial list of (loosely) AI-related stuff that I have found so far:
John Abercrombie (2K Boston) on the AI in Bioshock
At the GDC in San Francisco this past week, I had the opportunity to spend quite a bit of time with John Abercrombie of 2K Boston and the AI lead on Bioshock. It had been a heck of a week for the entire Bioshock team since their title had not only won many awards and accolades prior to GDC but also had a great showing at the Game Developers Choice Awards (they lost the Game of the Year award to Portal... in which there is no shame). Despite having been pestered relentlessly all week to speak about his AI work with the title (he probably talked about it as much as if he had given a lecture on in), he was gracious enough to sit down with me on Sunday morning and chat with me about it on tape.
I want to mention a few things here first...
I'm not a professional interviewer. I'm an AI guy just wanting to pick someone's brain.
We were sitting in a hotel lobby so there is a bit of background noise.
We didn't have a white board or anything else so we didn't really get "down to the metal" on any of these subjects - no code, no diagrams, etc.
We could have gone on forever that day, but Laurie and I had to catch a shuttle to the airport.
The one requirement his boss put on this interview was that I mention (loudly) that 2K Boston is hiring AI Programmers!
In case the above applet doesn't load or it is playing at the wrong speed, you can download the actual .mp3 file.
Here's some questions (paraphrased somewhat) that I asked and topics we discussed throughout the interview (listen to the audio for his answers and descriptions):
(0:41) How did you manage some of the issues with the potentially different factions? That is, splicers fighting splicers, the Big Daddies fighting the splicers, etc.
(5:35) Are the Splicers trying to get at the Little Sisters by default and thereby annoying the Big Daddies or is that just accidental?
(8:00) We discuss the game design mechanic of being able to choose the time and place of your "boss battle" and then actually wander around and watch the boss (Big Daddy) interact - even in combat with the Splicers.
(11:30) John talks about how the Splicers react to being cornered by the Daddies.
(12:50) What other things were you doing with the perception systems?
(19:35) We discuss how the enemies (e.g. the grenadiers) will adapt their tactics to you... both as an intelligent reaction but also to adapt the gameplay to specific difficulties in dealing with the interface and some plasmids.
(21:28) John talks about a small horror story with regard to ballistic physics and the "rifleman's rule".
(25:19) John talks about how the Daddies will use things like proximity grenades to box you in - but that how the Splicers don't even notice them.
(27:23) John talks about how the design decision surrounding whether to have the Splicers and Daddies avoid fire.
(28:13) I ask about the different tactics that the enemies use and how they select between them. Also, how they had to do workarounds to keep players from exploiting things like the pathfinding grid. He goes into detail about how this was beginning to get computationally expensive.
(34:26) What's your biggest horror story from the whole process? (John responds with an amusing anecdote about some early behavior tests.)
(37:24) What's the coolest thing that you pulled off?
(38:53) On Soren Johnson's scale from "good AI" to "fun AI", where do you think Bioshock fits?
(40:50) Do Splicers continue to spawn on a level until you leave it?
(43:00) We briefly digress into talking about the audio (which won awards).
(44:28) Not counting development time, how many times did you play through the game?
(49:04) John tells the story about his wonderful moment after the game is shipped. (As game developers, don't we all want to hear this?)
(Total length 50:56)
If you want to hear more of John's comments on various subjects, you can listen to the GDC AI Roundtable audio files and read my notes here. He spoke up once or twice in there.
Again, I want to thank John for taking the time with me for the interview... and being a pretty good companion throughout the week of GDC. I enjoyed it quite a bit.
This interview brought to you in association with...
I'm in the process of uploading all my GDC-related things to this page. You can actually listen to my audio of the 3 AI roundtables and read my (barely comprehensible) notes that I furiously took during each. Also, it has links to the pictures that I took during the roundtables and the AI Programmers Dinner on Friday night.
On that page, I will also be posting other AI-related tidbits such as my notes from lectures such as those by Soren Johnson's (Civ 4), Damian Isla (Halo 3), and Peter Molyneux (Fable 2). Give me a few days to get it all straightened out, though.
Also, I sat down with John Abercrombie of 2k-Boston on Sunday morning and spoke with him about the AI that he did for Bioshock. That should be posted on Wednesday. Look for it over on Post-Play'em.
(Remember to tap the RSS feed to keep up with these additions and all other AI-related things.)
One final note about GDC... it's always an exhilarating week... but it sure does make my head hurt!
The author makes some great points. One is about the wall that developers seem to run up against: We can make for some great "live" behavior that looks new and fresh - until we run out of assets (via space on the CD or dollars in the budget) and we start to repeat those fresh behaviors. At that point, the facade is exposed and things start to get stale. It goes to show that, at least with today's technological limitations, the Turing Test will always fail as long as there is no time limit on the test. Until we can break away from entirely designer-constructed content, our AIs will eventually expose themselves
The second point is something that is actually born from the past when we couldn't stuff a lot of fresh content into our agents - we faked it. He points to a technique that has been used over and over: let the player's mind be the best brush for coloring in the AI. There is a lot of power in that. However, one caveat is that we can't necessarily tell what the player is going to be thinking. Sometimes this is good and sometimes it can make for disappointment. Still, it makes for a lot of fleshing out of the perception of our AI without a lot of effort.
The solution seems to be a constant balancing act between two extremes. What really needs to be modeled in great detail and what can I fake entirely? Aahh, such is the quandary.
Anyway, I enjoyed the reading and personally plan to keep checking on neuRAI. Good work so far!
