Jump to content

  • Log In with Google      Sign In   
  • Create Account

Neural Network - Discussion


Old topic!
Guest, the last post of this topic is over 60 days old and at this point you may not reply in this topic. If you wish to continue this conversation start a new topic.

  • You cannot reply to this topic
103 replies to this topic

#41 Kylotan   Moderators   -  Reputation: 3338

Like
0Likes
Like

Posted 23 July 2008 - 10:56 PM

Quote:
Original post by shurcool
He said he's working on a final year research project. Key word is research.


You have misunderstood me. I fully support the idea of doing research into these things. I was just pointing out that the academic aim of wanting to get a certain tool to be able to perform a certain task is different from the industrial/pragmatic aim of choosing the tool for the task that involves the least risk.

Quote:
Quote:
You could potentially spend forever adjusting inputs, outputs, and hidden layers to try and get your neural network doing something useful, with no guarantee of getting anything that is good enough to be playable, or you can pick a method that explicitly accounts for all the scenarios a developer can envisage and get it working more reliably.

And what happens in a scenario that the developer did not originally envisage?

IMO, this is where the AI can come closest to 'making or breaking' the game - those unexpected but possible scenarios.


Yet they could still appear in neural networks, if you didn't think to include such things in your training data. Perhaps you get lucky and the net generalised to cover that case, and perhaps it didn't. You're not guaranteed to be any better off. So when you have a goal to meet and other tools available, tools tried and tested in many other applications, you use them.

Quote:
I now realize I wouldn't want to go into game development if it ends up involving nothing but spitting out cookie-cut, run-of-the-mill games.


No need for the hyperbole, really. If you have a job to do, then you have a job to do. You can't just expect to be allowed to spend months on R&D to try and come up with a new way of approaching something that isn't guaranteed to work, when there are existing tools that are guaranteed to work. Do that at university, or when self-employed, or when you've worked your way up to a position where you can get funding for such approaches. You'll be lucky to find many jobs in any industry that allow you to spend your wages playing with academic toys that are unproven in the area you're working in.

Sponsor:

#42 Kylotan   Moderators   -  Reputation: 3338

Like
0Likes
Like

Posted 23 July 2008 - 11:09 PM

Quote:
Original post by sion5
Truth is academia is there to encourage innovation.

But it is also there to prepare people for industry and employment. A balance has to be struck.

Quote:
I absolutely love playing games as much as I like trying to create them but it really irritates me that games should be at the forefront of A.I development yet subjects like statistics and robotics are way in front?!

These areas are in front because improved AI is essential for their functioning, so there's a lot of money pushed in that direction. Games arguably don't require great AI, and certainly not pioneering AI. It would be great if they had it... but there's no market forces really calling for it. So change is more likely to come from below, from an experimental prototype showing great potential.

You'll encounter less resistance if you try and go with that flow!

#43 sion5   Members   -  Reputation: 100

Like
0Likes
Like

Posted 23 July 2008 - 11:21 PM

Ok, so since starting this discussion I have read many more journals, articles and discussions on NN's. My conclusion is that NN's are not an absolute solution, BUT they can help form a solution quite nicely.

Another thing I found with NN's is their problem specific, I think alot of people got narky because I mentioned using a NN for automating an agent. Ok, so its not the best way to solve that PARTICULAR example. Now consider you had a game (NERO is an example) where your given a team of soldiers and you have to train them by putting them through military training exercises of your choice. Once you have trained your soldiers to a level your happy with or set period of time, you are then placed in a battlefield with another human players set of soldiers and see who wins. Correct me if im wrong but the only way to create a game like this would be using neural networks?? Not only this, as Risto Miikulainen said in his paper "Creating Intelligent Agents in Games" you are now starting to create new genres of games (which in my opinion the industry needs)

#44 bitshit   Members   -  Reputation: 163

Like
0Likes
Like

Posted 23 July 2008 - 11:33 PM

About previous research in NN applied to games; I once came across a project which expirimented with NN's applied to a racing game, with very good results:

http://togelius.blogspot.com/2006/04/evolutionary-car-racing-videos.html
(Also check out his newer blog entries)

Also I found this talk very interesting:



#45 Hnefi   Members   -  Reputation: 386

Like
0Likes
Like

Posted 23 July 2008 - 11:35 PM

Quote:
Original post by sion5Now consider you had a game (NERO is an example) where your given a team of soldiers and you have to train them by putting them through military training exercises of your choice. Once you have trained your soldiers to a level your happy with or set period of time, you are then placed in a battlefield with another human players set of soldiers and see who wins. Correct me if im wrong but the only way to create a game like this would be using neural networks??

No, there are other ways of creating general, adaptive behaviour. Remember, neural networks can't do anything that can't be done using other methods. For training combat agents in an RTS-like game, I'd probably prefer Bayesian networks. Support vector machines using the kernel trick is another alternative that is often preferred over NN's. I'm sure there are several more alternatives available.


#46 shurcool   Members   -  Reputation: 439

Like
0Likes
Like

Posted 24 July 2008 - 03:15 AM

Quote:
Original post by bitshit
About previous research in NN applied to games; I once came across a project which expirimented with NN's applied to a racing game, with very good results:

http://togelius.blogspot.com/2006/04/evolutionary-car-racing-videos.html
(Also check out his newer blog entries)

Also I found this talk very interesting:


I think you may be the first person to provide something the OP originally asked for (I missed some posts, so I could be wrong).

I read that blog and it was very interesting and thought-provoking, thanks.

#47 IADaveMark   Moderators   -  Reputation: 2532

Like
0Likes
Like

Posted 24 July 2008 - 04:00 AM

Quote:
Original post by sion5
Truth is academia is there to encourage innovation. I'm sorry but anyone can work in a factory pushing out the same product one after the other, but it takes academics to say "Hey wait, surely this can be done better?".

This is such a load of arrogant crap it is bordering on invalidating the usefulness of this entire thread and disqualifying you from further consideration on any relevant subject matter. 99% of the innovation in the modern world has come from outside academia. In the games industry, much the same can be said.

Quote:
Graphics and Audio has come on leaps and bounds in the past few years but where is A.I??

Because they are vastly different problems. The innovation and improvement curves are not going to be similar.

Quote:
If everyone's attitude is that we have found the best solution then there will never be an advancement in this domain.

Who is this "everyone" of which you speak? Every single time I sit down to work on my stuff, I'm trying to do something better. Every time I crack open the new AI Wisdom book, I see something from a front line dude that makes me say "damn... someone found a better way" - and usually it was because they were trying to solve a problem in their own projects. (You have read all the AI Wisdom books, right?)

Quote:
Back to subject. Are there any readers who are working on/ have worked on high profile games that have tried using NN technology?

There used to be material on that in the early AI Wisdom books... but not in the most recent one. It just hasn't caught on because people haven't found a use for it. Coincidentally, those articles often come from academic individuals and teams and NOT from the industry peeps.

Seriously... my suggestion to you is to do a little more reading. Do a little more browsing the web. The information is not going to come to you here. You are going to need to go to the information. If you want to give the forums at AIGameDev a try, have at it - there's a more active community there with a lot of pros... but I'm quite sure you will get a similar message.

An interesting exercise for you would be this... make a list of all the possible things you think an AI agent needs to do in a game. Pathfinding, steering, animation control, cover processing, decision making, planning, state management, cooperative interaction, etc... Then cull it down to the stuff that could be dealt with by a NN. Then list all the other ways that the same type of thing could be dealt with. List the pros and cons of each method. (if you don't know, you are already working from behind.) Then cull that down by what sorts of requirements the production game space needs. (e.g. computation speed, production speed, predictability, control, stability, etc.) Rank accordingly. This may be rather illuminating.

We've been trying to tell you... but after all, we aren't academics like you - therefore we don't know shit. It's up to you and your fellows to change the world. We just turn wrenches.
Dave Mark - President and Lead Designer of Intrinsic Algorithm LLC

Professional consultant on game AI, mathematical modeling, simulation modeling
Co-advisor of the GDC AI Summit
Co-founder of the AI Game Programmers Guild
Author of the book, Behavioral Mathematics for Game AI

Blogs I write:
IA News - What's happening at IA | IA on AI - AI news and notes | Post-Play'em - Observations on AI of games I play

"Reducing the world to mathematical equations!"

#48 IADaveMark   Moderators   -  Reputation: 2532

Like
0Likes
Like

Posted 24 July 2008 - 04:06 AM

Quote:
Original post by Hnefi
Quote:
Original post by InnocuousFox
Regardless of the tool, any decision system is at the mercy of how many inputs are hooked up to it. If you fail to include an input as a possible critieria and yet that piece of information becomes the difference between two otherwise similar scenarios, your agent will not know what to do. Again, this is regardless of the tool used - NNs, BTs, HFSMs, whatever. It's a knowledge representation issue first.

I'm not sure I understand what you mean. Neural networks are strictly signal processors; their input domain is perfectly defined.
[snip]
I don't see how it can be a knowledge representation issue, because NN's do not model knowledge explicitly. NN's deal strictly with signals, not abstract representations.

That's the point. Make a list of all of the inputs that you would require to make a decision about a certain problem. Those are your inputs, correct? What if you were to take one away? The decision model wouldn't be able to take that into account - and the resultant decision could suffer accordingly.

So, back with your original list, what if you haven't thought of everything? There may be a contingency where that one extra input that you forgot to include is the tipping point between stupid decision A and good decision B. However, your agent is stuck with stupid decision A because it doesn't know any better. The only knowledge that your agent had of the world was what you chose to provide it. Even if it is processing that information perfectly, it could still look stupid because of something you forgot.

(Note: this is for any decision tool... not just NN's)


Dave Mark - President and Lead Designer of Intrinsic Algorithm LLC

Professional consultant on game AI, mathematical modeling, simulation modeling
Co-advisor of the GDC AI Summit
Co-founder of the AI Game Programmers Guild
Author of the book, Behavioral Mathematics for Game AI

Blogs I write:
IA News - What's happening at IA | IA on AI - AI news and notes | Post-Play'em - Observations on AI of games I play

"Reducing the world to mathematical equations!"

#49 IADaveMark   Moderators   -  Reputation: 2532

Like
0Likes
Like

Posted 24 July 2008 - 04:16 AM

Quote:
Original post by sion5
Ok, so since starting this discussion I have read many more journals, articles and discussions on NN's. My conclusion is that NN's are not an absolute solution, BUT they can help form a solution quite nicely.

YES! Holy crap... about freaking time. If you wanted to use an NN for a small, contained situation, sure. Of course, as mentioned previously, it's likely that similar sort of decisions could be made by RBS, Expert Systems, Bayesian Networks (especially dynamic ones), etc. But at least you are out of the "Holy Grail" mentality.


Dave Mark - President and Lead Designer of Intrinsic Algorithm LLC

Professional consultant on game AI, mathematical modeling, simulation modeling
Co-advisor of the GDC AI Summit
Co-founder of the AI Game Programmers Guild
Author of the book, Behavioral Mathematics for Game AI

Blogs I write:
IA News - What's happening at IA | IA on AI - AI news and notes | Post-Play'em - Observations on AI of games I play

"Reducing the world to mathematical equations!"

#50 Hnefi   Members   -  Reputation: 386

Like
0Likes
Like

Posted 24 July 2008 - 05:34 AM

Quote:
Original post by InnocuousFox
Quote:
Original post by Hnefi
Quote:
Original post by InnocuousFox
Regardless of the tool, any decision system is at the mercy of how many inputs are hooked up to it. If you fail to include an input as a possible critieria and yet that piece of information becomes the difference between two otherwise similar scenarios, your agent will not know what to do. Again, this is regardless of the tool used - NNs, BTs, HFSMs, whatever. It's a knowledge representation issue first.

I'm not sure I understand what you mean. Neural networks are strictly signal processors; their input domain is perfectly defined.
[snip]
I don't see how it can be a knowledge representation issue, because NN's do not model knowledge explicitly. NN's deal strictly with signals, not abstract representations.

That's the point. Make a list of all of the inputs that you would require to make a decision about a certain problem. Those are your inputs, correct? What if you were to take one away? The decision model wouldn't be able to take that into account - and the resultant decision could suffer accordingly.

So, back with your original list, what if you haven't thought of everything? There may be a contingency where that one extra input that you forgot to include is the tipping point between stupid decision A and good decision B. However, your agent is stuck with stupid decision A because it doesn't know any better. The only knowledge that your agent had of the world was what you chose to provide it. Even if it is processing that information perfectly, it could still look stupid because of something you forgot.

(Note: this is for any decision tool... not just NN's)

I think I understand what you're trying to say now. Basically, if the domain is not structured as well as it could be, the decision process will suffer. I agree, but beside being trivially obvious, it doesn't really have anything to do with dealing with unforeseen situations which is what I was responding to shurcool about.

But sure, as previously stated, preprocessing/input configuration has a great effect on the performance of neural nets.

#51 Ohforf sake   Members   -  Reputation: 1832

Like
0Likes
Like

Posted 24 July 2008 - 09:25 AM

Did anyone post this link already?
http://www.gamedev.net/reference/articles/article1988.asp

However I think you are too much focusing on FPS-like games, which is not exactly the genre where you want extremely intelligent opponents. Rather "realistic" behaving but easy to kill opponents.

#52 sion5   Members   -  Reputation: 100

Like
0Likes
Like

Posted 24 July 2008 - 08:15 PM

Quote:
Original post by InnocuousFox
Quote:
Original post by sion5
Truth is academia is there to encourage innovation. I'm sorry but anyone can work in a factory pushing out the same product one after the other, but it takes academics to say "Hey wait, surely this can be done better?".

This is such a load of arrogant crap it is bordering on invalidating the usefulness of this entire thread and disqualifying you from further consideration on any relevant subject matter. 99% of the innovation in the modern world has come from outside academia. In the games industry, much the same can be said.


InnocuousFox, since this post has started you have been rude and flipant. I dont consider you helpful and quite frankly I haven't taken any positives from anything you have said.

Why is it that every other poster can structure their reply in such a way that its informative and friendly (even if they disagree with my views) yet you feel the need to have a dig at MY topic of research. If this gets me excluded from further discussion then I appologise to everyone for lowering the tone. There's only so much I can take. For me to get a job in the industry I need to have qualifications and show an ability to learn, the fact that your president of a company could very well mean this is not the approach you taken but it doesn't work for everyone!

#53 IADaveMark   Moderators   -  Reputation: 2532

Like
0Likes
Like

Posted 25 July 2008 - 03:48 AM

Quote:
Original post by sion5
InnocuousFox, since this post has started you have been rude and flipant.

Methinks you need to reread my first few responses... or the first two pages.
Quote:
I dont consider you helpful and quite frankly I haven't taken any positives from anything you have said.

That is often the reaction when people don't get the answers they want to hear.

Of course, then you dropped this bomb.
Quote:
Original post by sion5
Truth is academia is there to encourage innovation. I'm sorry but anyone can work in a factory pushing out the same product one after the other, but it takes academics to say "Hey wait, surely this can be done better?".

And that is where I severely lost respect for you. You dropped into the groove that has many of us exasperated with academia in the first place. There is an arrogance, condescension and Messiah complex all rolled into those two sentences of yours... and yet, the industry continually rejects (most of) what (many of) the academics that you laud so highly have to offer.

I think that your approach to this entire conversation has illustrated why in microcosm... that your attitude has been "obviously you wrench-turners are missing the point!" You even challenged us with "prove that it doesn't work" - which is a ridiculous statement. Which brings me to the next tidbit...

Quote:
Why is it that every other poster can structure their reply in such a way that its informative and friendly (even if they disagree with my views) yet you feel the need to have a dig at MY topic of research.


Allow me to return volley... why is it you feel the need to disregard anything that anyone has to say on the subject? In my first post, I warned you "be careful what you wish for." You got feedback and steadfastly refused to hear it much less accept it. (e.g. "show me proof")

Quote:
If this gets me excluded from further discussion then I appologise to everyone for lowering the tone. There's only so much I can take.


And there's only so many times we can tell you "been there - done that." *shrug*

Quote:
For me to get a job in the industry I need to have qualifications and show an ability to learn,


First, after your arrogant statement above, why would want to descend into the uninspired trenches of the industry when all the thinking happens in the ivy-covered walls of academia? Putting that aside, no one has discouraged you from acquiring qualifications and knowledge, nor has anyone argued that the ability to learn is not a prime qualification in and of itself. (In fact, read Damian's post I linked to on page 1 and he says much the same thing.) However, I believe that your approach in this whole conversation was insisting that the industry needs to learn the technology that you want to pursue rather than you learning what the industry as a whole has found to work.

Seriously... reread the thread in its entirety. Read it aloud. Read everyone's posts... including your own. And then, like a good academic researcher should be, back off a step or two into the realm of objectivity and see what is really being said by everyone... and what went wrong.
Dave Mark - President and Lead Designer of Intrinsic Algorithm LLC

Professional consultant on game AI, mathematical modeling, simulation modeling
Co-advisor of the GDC AI Summit
Co-founder of the AI Game Programmers Guild
Author of the book, Behavioral Mathematics for Game AI

Blogs I write:
IA News - What's happening at IA | IA on AI - AI news and notes | Post-Play'em - Observations on AI of games I play

"Reducing the world to mathematical equations!"

#54 IADaveMark   Moderators   -  Reputation: 2532

Like
0Likes
Like

Posted 25 July 2008 - 08:13 AM

Potentially relevant thoughts regarding "getting into the industry"...

How to Become a Game AI Developer by Paul Tozour.
AI Developer Interview Questions by Paul Tozour.
Thoughts on Industry / Academic collaboration by Adam Russell (who happens to be teaching right now)
Dave Mark - President and Lead Designer of Intrinsic Algorithm LLC

Professional consultant on game AI, mathematical modeling, simulation modeling
Co-advisor of the GDC AI Summit
Co-founder of the AI Game Programmers Guild
Author of the book, Behavioral Mathematics for Game AI

Blogs I write:
IA News - What's happening at IA | IA on AI - AI news and notes | Post-Play'em - Observations on AI of games I play

"Reducing the world to mathematical equations!"

#55 Rockoon1   Members   -  Reputation: 104

Like
0Likes
Like

Posted 27 July 2008 - 08:15 AM

Lets state the most basic of facts in regards to various AI technologies:

All the technologies discussed are function(s) that take some number of inputs and produce some number of output(s), in an attempt to maximize or minimize some score or cost (even if that score is purely subjective such as 'it does what I want')

In this regard, an NN is no different than an FSM or any other methodology.

A key advantage to leveraging NN+GA as an approach to a problem is that YOU do not have to decide which inputs are important and which ones are not. Use all the inputs available and burn some CPU. The point of such an excersize is often that you do not trust your own judgement and instead will relegate the problem to 'Machine Learning', with an aim not to evolve the best 'thing' but instead to determine a measure of the relative worth of each input in regards to maximizing and minimizing.

This does not mean that at the production point of your product you are using NN's trained by GA's. It could mean that you then took that information that you garnered from ML and produces a hand creafted FSM out of it.

This isnt an either/or proposition. All these technologies are tools and if the tool works to solve the problem, then all other arguements are completely moot. The problem isnt always focused on the end result product, but rather a middle step on the way to that product.

I think many game developers have disregarded many of these tools in their race to get their product out the door. This isnt necessarily a bad thing. The companies score metric is almost always profit per year (always so if they are publically traded), which is often at odds with overall product quality. It is precisely at the academic level where quality and innovation are primary on the human cost metric.


#56 Timkin   Members   -  Reputation: 864

Like
0Likes
Like

Posted 28 July 2008 - 05:32 PM

*moderator hat on*
Everyone take a chill pill please. It's quite okay to have a strong opinion, particularly in the academia vs industry debate, but please try to keep the discussion polite... or at least avoid making directed, personal attacks at each other.

Thanks.

*moderator hat off*

On the original question of researching the use of NNs in games. That's quite valid. Go for it. Just don't expect anyone to actually use ANNs just because you might find a valid application for them. As has been pointed out several times in this thread, there exists, almost always, an alternative solution to a problem that an ANN can solve (and usually *how* it solves it is more easily and more widely understood). Doing research for research sake is not a good use of your time. You should be looking for quantifiably useful results. That is, research must have significance AND importance. Thus, you should be looking at problems and asking "can an ANN solve this better than the existing methods". Significant quantities of previous research though have shown that, generally, the answer is no.

Some comments on the parallel, off-topic discussions of game education and industry vs academic innovation...

In Australia over the past 5 years many universities have jumped onto the game dev/design education bandwagon... 10 years ago there were only 2 places in Oz you could go to study games. Now it's more like 20. This is a recognition of two things: 1) that there is strong demand for 'cool' courses (and those perceived as vocational) amongst high school graduates; and, 2) there is a demand from industry for graduates who have some basic understanding of the problems that must be overcome in the production of games software.

Traditionally though, the role of universities has been to develop scholarship and engender graduates with the skills for life-long learning. These skills can of course be learned outside of the university environment. The role of universities is not (or at least, should not be) to teach people how to do a specific job. These skills should be learned through practice, while on the job. Unfortunately, in this modern, economically focused age, universities have been forced to sacrifice scholarship for 'graduate outcomes' (meaning employment prospects) because industry does not want to bear the expense of training workers. The result is that universities now try to cater to what industry wants and what students want, rather than on what society needs. Hence the rise in games dev programs. (There is also another driver: market growth in the games industry due to the 'leisure lifestyle' of Gen Y... but that's a discussion for another day). We should not though expect universities to churn out people who are job-ready on day one. It simply isn't possible. They have a lot to learn and it's up to industry to choose those most capable of learning and employ them, when they have the need.

Having said that, there ARE very good degree programs teaching game development in a computer science/software engineering framework, where students learn fundamental skills applicable across a broad spectrum of IT roles, but also focus heavily on game development. One would expect that graduates from these programs are useful to industry. Sure, they're wet behind the ears and need to learn a lot... but at least they have some basic foundations from which to grow from.

As for innovation...

I cannot recall the source of the data, nor the exact figures (so please, take this with a grain of salt), but I remember reading that around 95% of innovation in IT was achieved by industry, rather than academia and that this was simply because it was industry trying to solve the day to day problems in software development. In other words, they needed a solution so they went out and developed one. That doesn't mean though that academia is a waste of space and money. The role of academia is NOT to produce commercial applications of knowledge, nor to produce knowledge with immediate commercial value (although this does happen from time to time). Indeed, because there is not an inherent, immediate commercial value in what academics do, many people denounce them as useless.

On the contrary though, academics are afforded the luxury of the time and money to investigate problems that *may* have a commercial value in the future (or may lead to an advancement of knowledge). In Australia we have two government funded research streams, provided by the Australian Research Council, to support this: Discovery grants and Linkage grants. These are aimed, respectively, at developing fundamental knowledge (discovery) and developing commercially viable applications of fundamental knowledge (linkage). The latter is always done in partnership with industry. Thus, at least in Australia, the role of academics is to solve the problems, or develop the knowledge, that industry has neither the time nor money to investigate, simply because they cannot guarantee a benefit to their bottom line. We get to look at the big picture, or the fuzzy, distorted picture that no one else can afford to look at, to find new solutions to old (or new) problems.

Principally, our aim is to inform industry of what is possible and to provide them with a strong foundation from which they can develop the solutions that they need. Both groups are necessary. Without industry, academia has no funding support (no one paying taxes that fund the research) and without academia, industry has to bear the cost of the research upon which their innovations are often based (and it's been shown time and again that industry cannot afford to do this). In the end, we all need to get along with each other, which, if I recall correctly, was the original comment in this post! ;)

Cheers,

Timkin

#57 Timkin   Members   -  Reputation: 864

Like
0Likes
Like

Posted 28 July 2008 - 05:35 PM

Oh, just a quick response to kirkd... if it weren't for Kolmogorov, who built on Markov's work, we wouldn't have our modern information age (including computers, electronic and photonic communications systems, the internet, etc)! So, it's probably a little unreasonable to suggest that Markov's work sat idle for 100 years until applications of Markov chains arose in speech recognition! ;)

Cheers,

Timkin

#58 IADaveMark   Moderators   -  Reputation: 2532

Like
0Likes
Like

Posted 29 July 2008 - 03:04 AM

Absolutely brilliant, Tim.
Dave Mark - President and Lead Designer of Intrinsic Algorithm LLC

Professional consultant on game AI, mathematical modeling, simulation modeling
Co-advisor of the GDC AI Summit
Co-founder of the AI Game Programmers Guild
Author of the book, Behavioral Mathematics for Game AI

Blogs I write:
IA News - What's happening at IA | IA on AI - AI news and notes | Post-Play'em - Observations on AI of games I play

"Reducing the world to mathematical equations!"

#59 FippyDarkpaw   Members   -  Reputation: 154

Like
0Likes
Like

Posted 29 July 2008 - 02:42 PM

AI for most games is relatively simple. Move there, shoot at this guy, take cover, etc... Training a NN for such simple tasks is pointless overkill.

NN are for complex tasks where the solution is either complex or not feasible to hand code. Thus most applications of NN are in solving complex engineering, robotics, and computer vision tasks.

If you want to (usefully) apply NN to games, think of a situation where coming up with a formula or hand-coded state machine to solve the problem would be extremely hard. For example, if you read about the NN implementation in Colin McRae 2.0 racing game, they had very complex car and track physics (mud track racing) and were unsuccessful hand-coding a good general purpose AI. Thus training NN drivers was a good solution.

Another example would be AI for a complex game like "Go" (each move leading to many times more decisions than Chess). So far nobody has successfully come up with a competent Go AI. Some type of Machine Learning will solve it ... eventually.

#60 IADaveMark   Moderators   -  Reputation: 2532

Like
0Likes
Like

Posted 29 July 2008 - 04:18 PM

NNs can pretty much handle only a static time slice and don't handle looking ahead (or behind) very well. That makes any sort of planning algorithm a little muddy.
Dave Mark - President and Lead Designer of Intrinsic Algorithm LLC

Professional consultant on game AI, mathematical modeling, simulation modeling
Co-advisor of the GDC AI Summit
Co-founder of the AI Game Programmers Guild
Author of the book, Behavioral Mathematics for Game AI

Blogs I write:
IA News - What's happening at IA | IA on AI - AI news and notes | Post-Play'em - Observations on AI of games I play

"Reducing the world to mathematical equations!"




Old topic!
Guest, the last post of this topic is over 60 days old and at this point you may not reply in this topic. If you wish to continue this conversation start a new topic.



PARTNERS