• Announcements

    • khawk

      Download the Game Design and Indie Game Marketing Freebook   07/19/17

      GameDev.net and CRC Press have teamed up to bring a free ebook of content curated from top titles published by CRC Press. The freebook, Practices of Game Design & Indie Game Marketing, includes chapters from The Art of Game Design: A Book of Lenses, A Practical Guide to Indie Game Marketing, and An Architectural Approach to Level Design. The GameDev.net FreeBook is relevant to game designers, developers, and those interested in learning more about the challenges in game development. We know game development can be a tough discipline and business, so we picked several chapters from CRC Press titles that we thought would be of interest to you, the GameDev.net audience, in your journey to design, develop, and market your next game. The free ebook is available through CRC Press by clicking here. The Curated Books The Art of Game Design: A Book of Lenses, Second Edition, by Jesse Schell Presents 100+ sets of questions, or different lenses, for viewing a game’s design, encompassing diverse fields such as psychology, architecture, music, film, software engineering, theme park design, mathematics, anthropology, and more. Written by one of the world's top game designers, this book describes the deepest and most fundamental principles of game design, demonstrating how tactics used in board, card, and athletic games also work in video games. It provides practical instruction on creating world-class games that will be played again and again. View it here. A Practical Guide to Indie Game Marketing, by Joel Dreskin Marketing is an essential but too frequently overlooked or minimized component of the release plan for indie games. A Practical Guide to Indie Game Marketing provides you with the tools needed to build visibility and sell your indie games. With special focus on those developers with small budgets and limited staff and resources, this book is packed with tangible recommendations and techniques that you can put to use immediately. As a seasoned professional of the indie game arena, author Joel Dreskin gives you insight into practical, real-world experiences of marketing numerous successful games and also provides stories of the failures. View it here. An Architectural Approach to Level Design This is one of the first books to integrate architectural and spatial design theory with the field of level design. The book presents architectural techniques and theories for level designers to use in their own work. It connects architecture and level design in different ways that address the practical elements of how designers construct space and the experiential elements of how and why humans interact with this space. Throughout the text, readers learn skills for spatial layout, evoking emotion through gamespaces, and creating better levels through architectural theory. View it here. Learn more and download the ebook by clicking here. Did you know? GameDev.net and CRC Press also recently teamed up to bring GDNet+ Members up to a 20% discount on all CRC Press books. Learn more about this and other benefits here.
Sign in to follow this  
Followers 0
rouncer

funny idea for an ann game

16 posts in this topic

What if the inputs of the neural network were not just an enemy character in the game, but inputs for how the screen scrolls and zooms, enemies are spawned, enemies react, die, what happens to the player when he touches different things...  basicly every single activity that happens during the game.

I was thinking you could train it all with backpropagation, you actually hand feed the neural network the motions of the game as if it was playing, then after it is trained it should be able to run the game for you. smile.png

 

It would be like a little man placing the game for you as you went through it. 

Edited by rouncer
0

Share this post


Link to post
Share on other sites
Maybe you should get some actual experience with ANNs before you get too excited about their possibilities. Start by writing ANNs that learn basic things, like a linear combination of things to predict another (an ANN with a single neuron, which is like linear regression), then XOR... Then you can try to reproduce the results of other people with things like character recognition. By now you'll realize that backpropagation has lots of issues and doesn't get you too far. You can then learn something about support vector machines, deep belief networks, etc. Then go back and read your own post above, and see if it still makes sense.
2

Share this post


Link to post
Share on other sites

A good starting point might be Perceptron, then Hopfield and then FeedForward. And in the mean time you will learn different training and error calculation algorithm like- hebb's rule, delta rule and after that, Backpropagation.

 

Good Luck.

1

Share this post


Link to post
Share on other sites

Maybe you should get some actual experience with ANNs before you get too excited about their possibilities. Start by writing ANNs that learn basic things, like a linear combination of things to predict another (an ANN with a single neuron, which is like linear regression), then XOR... Then you can try to reproduce the results of other people with things like character recognition. By now you'll realize that backpropagation has lots of issues and doesn't get you too far. You can then learn something about support vector machines, deep belief networks, etc. Then go back and read your own post above, and see if it still makes sense.

 

Why do I feel like this is another example of "magic word" syndrome? That the OP is fascinated with "ANN" and keeps saying it over and over because he thinks it sounds cool despite having very little knowledge about what it really does or the (more suitable?) alternatives?

1

Share this post


Link to post
Share on other sites

Well it works like natural motion... except instead of controlling one character, it controls multiple characters. (and the camera)

I dont see how if natural motion can work, this cant...

0

Share this post


Link to post
Share on other sites

That's not the point. Your argument is very much like, "well, you can use a hammer on a nail, so why can't you use a hammer on a screw as well?" Right tool for the job, sir.

 

Is your goal to accomplish a gameplay trick or is your goal to use an ANN to do... something?

Edited by IADaveMark
0

Share this post


Link to post
Share on other sites

I believe he wants to use an ANN for all of the game's logic.

 

I don't believe he understands the point (If any) of ANN's.

0

Share this post


Link to post
Share on other sites

I believe he wants to use an ANN for all of the game's logic.

 

I don't believe he understands the point (If any) of ANN's.

So what's the point (if any) of ANN ?

2

Share this post


Link to post
Share on other sites

Personally, I think they're better then using a pure state based approach for strategy games' fight or flight decisions, but it really depends on the complexity.. Other then that, I can't think of somewhere where it's easiest, or worthwhile at all to implement something like this.

 

Maybe after it's been explored for a while and there's a multitude of third party API's to work with them easier, assuming it's worth creating those (Which I doubt it is).

0

Share this post


Link to post
Share on other sites

so you dont like exploring new ideas, youd rather everyone else do that for you.  

to each their own i guess.

Edited by rouncer
-4

Share this post


Link to post
Share on other sites

so you dont like exploring new ideas, youd rather everyone else do that for you.  

to each their own i guess.

 

And with this, you have jumped the proverbial shark.

 

ANNs are not even remotely "new". They are also hopelessly over-hyped. They are a simple pattern-matching algorithm poorly equipped to handle most of the situational reasoning tasks necessary for game AI or many other kinds of AI applications. Even in the traditional machine learning arena, NNs are somewhat considered passe since there are far better alternatives.

 

But I see you don't like researching ideas beyond what you Obviously Know Is Best. You'd rather everyone else do that for you.

 

To each his, own I guess.

0

Share this post


Link to post
Share on other sites

Personally, I think they're better then using a pure state based approach for strategy games' fight or flight decisions, but it really depends on the complexity.. Other then that, I can't think of somewhere where it's easiest, or worthwhile at all to implement something like this.

 

Actually, while I agree that pure state based approaches in strategy games are a problem, a NN isn't the answer really. When dealing with a huge influx of variable data such as we have in more complex situations, a utility-based approach is by far preferable. As with a NN, there are a ton of numbers being balanced and played against one another. The difference is, in a utiltiy-based system, you know what those numbers are doing with their relationships to each other. An NN, by its very nature, is opaque. You can't even lift the lid and point to something and say, "and this is why it made that decision". There is no such entity to point at in an NN. It just comes out the meat grinder.

 

They're both number crunchers... one method is based on intelligent design -- the other on hope and fairies.

0

Share this post


Link to post
Share on other sites

What if the inputs of the neural network were not just an enemy character in the game, but inputs for how the screen scrolls and zooms, enemies are spawned, enemies react, die, what happens to the player when he touches different things...  basicly every single activity that happens during the game.

I was thinking you could train it all with backpropagation, you actually hand feed the neural network the motions of the game as if it was playing, then after it is trained it should be able to run the game for you. 

I don't want to add to the previous heartfelt advice against neural network misapplication, because stubbornly defying contrary opinions might still be a useful learning experience; this description of what you want to do is much more worrying than the risk of wasting time by trying an inadequate technique, because you don't want to try a technique, you want a magic wand. Wishful thinking and learning rarely mix.

 

While trying to develop a bot to play your game is a fine objective, you don't seem to approach it on a sound problem-solving basis, hoping instead that applying a neural network is going to be easy and effective: this sort of a priori preference for a certain solution is the opposite of good engineering and design, and it would be equally bad in the case of a good technique.

 

You don't even state clearly what sort of game you are thinking of, neglecting the analysis of what an AI for your game needs to be able to do and what are the difficulties and non-difficulties in such tasks, which is the first step in choosing appropriate AI architectures and algorithms and/or modifying game rules to make the AI perform better (for example, simplifying game state to reduce the amount of training needed and facilitate unsupervised trial and error learning). Do you expect this work to disappear?

2

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!


Register a new account

Sign in

Already have an account? Sign in here.


Sign In Now
Sign in to follow this  
Followers 0