Game AI been neglected because of graphics?

Started by
54 comments, last by njpaul 18 years, 11 months ago
Quote:Original post by jollyjeffers
As others have said, it's going to be a while before AI takes center stage - but with the advent of these multi-processor/multi-core systems, and the inevitable switch to multi-programming, I reckon AI will get a chance at the big time.... [smile]. Fingers crossed the argument that processing resources are limited will become null and void.


I submit that this has alrady been done a couple of times with some games, where the marketing made a huge deal about how amazing the AI was going to be...and then players were pretty much let down hard when the game hit the market (I'm thinking UT Online and various RTS games here). That put a bit of a crimp into making claims that were perhaps over the top.

At the GDC roundtables we've occasionally had folks asking what to do if they built their AIs too smart and/or too hard. We've always told them they should be so lucky...

Quote:

If a couple (or more!) big name games take the time to put some truly powerful AI into things, the sort of stuff that gets people going [oh] at how damn impressive it is, then they'll raise the bar. Raise the bar and others will almost certainly follow...


This is absolutely the case, and I think we've seen it slowly come true across genres. Games that don't do something in particular that has become widespread quickly get slammed by the reviews.

At this year's GDC we saw an incredible number of design walkthroughs that had a huge amount (I thought) in common with each other. Lots of different games but the basic AI engine designs were very similar, as if developers have been trying lots of things and slowly settling on a small handful of approaches that give them the design flexibility they need, which raising the bar another notch.

Ferretman
ferretman@gameai.com
From the High Mountains of Colorado
GameAI.Com

Advertisement
Quote:Original post by Zodiak
Well, I just think that when one DOES create an awsome AI, the gaming industry will get that boost like with physics. What I mean, is if you haven't heard of a certain game, and then it comes out with average graphics etc. but with some awsome AI system, it will immediately be noticed... It's just a matter of making an excellent AI system, that's all. Because above all, people tend to admire AI the most when it's there. So the game will be a huge success, with millions of people going like 'Oh, Joe, check it out... Yesterday that <beep> had actually outsmarted me... it's so fun! I created a line of defence in the north, but that <beep> anticipated it and attacked me from the rear..." something like that. It's way way more fun to play with good AI than with graphics + physics because without AI they mean nothing
(unless we are talking about multiplayer).



I like your train of thought but have a problem with your example...specifically, how will the player know that the AI "anticipated" his line of defenses and hence attacked from the rear? Unless the AI tells him somehow, or perhaps the player's avatar "debriefs" the AI after the fact, the player doesn't really know whether the AI anticipated him or cheated.

One of the things one loses when playing against an AI is the boast-and-goad factor you have when it's your buddy on the LAN....not sure how to solve that one though.

Ferretman
ferretman@gameai.com
From the High Mountains of Colorado
GameAI.Com

For computer gamers, this means almost nothing, but for console gamers Halo and AI became synonymous. The fact that enemies reacted and spoke trash and there was strategy that you and a teammate could perform made the worthwhile. It'll be interesting to see what Halo 2.5 on the XB2 will bring. Prettier graphics or more clever AI (hopefully both). You can definitely sell a game on AI. The problem is delivering and not letting the publishers force you to concentrate on graphical eye candy.

Beginner in Game Development?  Read here. And read here.

 

Quote:Original post by Alpha_ProgDes
For computer gamers, this means almost nothing, but for console gamers Halo and AI became synonymous. The fact that enemies reacted and spoke trash and there was strategy that you and a teammate could perform made the worthwhile. It'll be interesting to see what Halo 2.5 on the XB2 will bring. Prettier graphics or more clever AI (hopefully both). You can definitely sell a game on AI. The problem is delivering and not letting the publishers force you to concentrate on graphical eye candy.


The designers behind HALO and HALO 2 had some of the very best presentations at the GDC I've seen. They got a standing ovation after the end of their presentation back in 2003...it was simply superb (and I suspect many of us were envious of their design tools).


Ferretman
ferretman@gameai.com
From the High Mountains of Colorado
GameAI.Com

(Hi ferretman, good to see you around here again!)

Personally, I think that AI and physics will necessarily have to advance hand-in-hand. If the games characters are unable to meaningfully interact with a complex, realistic environment, which they need to do to offer meaningful interactions with the player, then the player is going to very quickly lose interest in those characters and hence the game. For example, if the player can bounce grenades through a doorway to kill the enemies in a room, then the NPCs of the game should be able to do the same. If all they can manage is to walk into the room shooting at anything they see, then the player is going to feel very quickly that they are up against weak opponents.

As to the comments about how does one 'know' when the game AI was 'intelligent', yes that's an issue that needs to be resolved (and I haven't seen any convincing, non-scripted answers to this yet). However, in my opinion, most people would be convinced of some level of intelligence in an opponent that adapts to the players strategies to overcome them. So, in the RTS genre, for example, adapting strategies from maps to map (using analogous scenarios and past map experiences to infer the possible activities of the player) and adapting between games (using direct experience of that player to define alternative strategies that are challenging to the player). The ultimate benefit of this latter form of dynamic strategy formation is increased replayability of the game and hence better value for money form the players perspective.

Cheers,

Timkin
AI being neglected? Not so much. Original and innovative game ideas being neglected? Definately. Time for the indie scene to come up with the ideas of the future.

This topic is closed to new replies.

Advertisement