[Discussion] Will the AI cheat

grasspuddle

Newcomer

6 000g2g pts

13 years ago

May 13, 2012, 3:37:32 PM

I like adding a bonus to AI for difficulty. I wonder if 'personalities' will be from race to race, or if each race will have more than one personality.

MT4K

Newcomer

MT4K

Newcomer

13 years ago

May 1, 2012, 7:56:29 PM

Becks wrote:
Very nice to read this. But I have one question. Is the AI able to learn from the behavior of the player?

As awesome as a self learning a.i would be. I imagine it's very hard to programme though otherwise i think more games would have used it. I could be wrong of course as i know nothing about programming.

MODVieuxChat

Chameleon

Truth is a chameleon. Herbert

MODVieuxChat

Chameleon

25 400g2g pts

13 years ago

May 1, 2012, 9:49:16 PM

The hardest with learning AI is to... learn. You need a lot of iteration to get some not so bad AI. And they need to battle not only each others but also humans to be at least effective.

MODNosferatiel

Informer

"God's in his heaven, all's right with the world." Nerv Motto, Neon Genesis Evangelion

MODNosferatiel

Informer

47 300g2g pts

13 years ago

May 1, 2012, 10:08:32 PM

VieuxChat wrote:
The hardest with learning AI is to... learn. You need a lot of iteration to get some not so bad AI. And they need to battle not only each others but also humans to be at least effective.

The typical problem for that kind of thing is "overtraining". For a program to learn, you set a range of input variables and define your desired output, e.g. winning the game. Then you have to put it into the environment it will be used in, the game e.g., let it work against s.o. or s.th. and then repeat it until you've found a set of functions of your input variables that work best at giving you the desired output. That is called training.

If consequently done against s.th. that is rather stable, like another AI with fixed parameters, this method will of course win in the long run, but might totally fail against a human who adapts.

If you train too long, you might end up with an AI that is capable of only winning that one scenario you trained it for and totally unable to do anything else.

If you don't train it long enough, it might be a bit of a loon and do totally unproductive things.

And making it learn during one game in itself, that is really hard to achieve. You'd probably have to do s.th. black and white-like and repeat some feedback on some output of the AI constantly for it to have some idea where to shift its priorities. In a 4x-game that might just as well mean the faction the AI controls loses before it achieves any kind of normal gameplay chance.

Correct me if I'm wrong on any of these points, please. There should be a lot of people in this forum who know more about AI controlling than I do of multivariate analyses and programming. XD

Damntry

Newcomer

Damntry

Newcomer

12 400g2g pts

13 years ago

May 5, 2012, 10:49:27 AM

I don´t think there´s ever been a relatively complex game in which the AI doesn´t cheat, specially strategy games. It´s good enough if the cheats does not get noticed.

Inquisitioner

Officer

Inquisitioner

Officer

20 000g2g pts

13 years ago

May 5, 2012, 12:20:12 PM

Damntry wrote:
I don´t think there´s ever been a relatively complex game in which the AI doesn´t cheat, specially strategy games. It´s good enough if the cheats does not get noticed.

I have to agree. Since they aren't players, they're the game itself.

Aerensiniac

Newcomer

Aerensiniac

Newcomer

13 years ago

May 5, 2012, 12:39:46 PM

Becks wrote:
If I remember right, SpaceTroll said that "you can compare the AI to a baby. A complex brain but it doesn't know how to use it well." Therefore I think that the AI will not cheat. The baby needs only some training.

How is babe formed... :eek:

Well if its a baby, then it must have really caring parents cause i find myself constantly encountering 2 map size civilizations by the time i colonize my 6th planet (~Turn 50)

halflotus

Newcomer

halflotus

Newcomer

9 900g2g pts

13 years ago

May 7, 2012, 3:20:25 PM

In my mind, giving a "bonus" to AI FIDS output is cheating.

pocketknife

Newcomer

pocketknife

Newcomer

13 years ago

May 9, 2012, 5:35:49 PM

VieuxChat wrote:
The hardest with learning AI is to... learn. You need a lot of iteration to get some not so bad AI. And they need to battle not only each others but also humans to be at least effective.

This can be done "genetically" with a reporting function back to amplitude. treat every game as a data point and go from there. Slowly, the AI would find a strategy that works against most comers. You can force the AI to balance against each other too by running playerless games; This would probably be the starting basis for a genetic AI. Anyway, They are looking to sell a 4x, not make breathtaking AI breakthroughs. Its probably quite a hard problem to tackle.

I am curious about the agent in-game learning. If I build a laser heavy armada, do they move to counter my change in tactics quickly? That sort of thing. Round to round learning.

Becks

Newcomer

Becks

Newcomer

13 years ago

May 1, 2012, 7:52:06 PM

Very nice to read this. But I have one question. Is the AI able to learn from the behavior of the player?

DEVSlowhands

Literary Dev

"Twenty years from now you will be more disappointed by the things that you didn't do than by the ones you did do."

DEVSlowhands

Literary Dev

39 800g2g pts

13 years ago

May 25, 2012, 8:44:46 PM

As there are occasional questions on the forums about the AI and how it works, I am giving the thread a little nudge.

VIPXorUnison

Stellar

Fan of the Endless Universe since the ES Alpha. Attended the Gamescon 2012/2015/2016/2017.

VIPXorUnison

Stellar

43 700g2g pts

13 years ago

May 25, 2012, 10:39:47 PM

Then I'm going to do my best keeping it up for a while, since I have to add something myself anyway.

I think it's fine if the AI cheats a little, it just has to be done in a specific way. Increasing the FIDS output on the AI is one way of cheating I deem fine. I remember Space Empires 5 giving you the option to let the AI cheat separately from all other options and I always used it to get a little more challenge. As for ES I think the AI does kind of okay during the game but it has to become somewhat stronger, I think the AI is good when on impossible the player has to be at least pretty skilled to keep up with them. So far I'm plenty able to stomp 2 empires on Impossible. Without any wars between any of the factions I'm usually about 1,5-2 as strong as both enemy empires at round 100 on fast, both enemy empires together that is.

But appart from the AI still being a little weak I really like what I see and after reading ThorTillas post I'm optimistic the AI is going to be very good upon release.

stevenmc409

Newcomer

stevenmc409

Newcomer

13 years ago

May 26, 2012, 12:45:37 AM

Good thread I'm wondering if the AI factions will work together when faced with a common enemy and if they will be able to incorporate strategy derived by players and posted on these forums (examples. Destroyer swarms, Immediately attack the Cravers, harassment wars to disrupt enemy FIDS etc.)

Zenicetus

Old Timer

Zenicetus

Old Timer

17 900g2g pts

13 years ago

May 26, 2012, 4:26:36 PM

stevenmc409 wrote:
Good thread I'm wondering if the AI factions will work together when faced with a common enemy

That's a tricky one. Alliances between factions to beat another (non-player) faction could be interesting. The typical "gang up on the human player when he gets too big" alliance is something else though. It's become a convention in strategy games to slow down a winning player, but it's annoying when it's too predictable.

and if they will be able to incorporate strategy derived by players and posted on these forums (examples. Destroyer swarms, Immediately attack the Cravers, harassment wars to disrupt enemy FIDS etc.)

IIRC, the way this was done in GalCiv2 was that the devs would track player strategies discussed in the forums, and then modify the AI routines to cope with common player strategies as each update was released. That's a more reasonable goal, obviously, than expecting the AI to learn on the fly. If the game is continually updated after release, I hope that's the plan.

DoCHam

Newcomer

DoCHam

Newcomer

13 years ago

May 27, 2012, 11:00:05 PM

I played my first game on easy and the AI was outproducing me three to one by the time I saw it for the first time, and two to one right from the start. He showed up at turn eighty with significantly more, better, larger, and bigger fleet stack. Except for the wormhole bottle neck and some early Hero wins the game would have been done. It had a massive advantage, a seemingly endless supply of ships, and also had the map covered well before I did my half. Now this was my first game and all but there is no way things were equal. I never lost a battle for the first 140 turns, and hardly lost a ship BUT the AI was still ahead on points 3 to 1 by the time the game died to a heap error. So after blowing up hundreds of ships, maxing one Hero out at 20 and the others almost maxed out as well and it sure felt like the AI still had 10-15 times more ships then I did.

I'll give it a few more tries but my first impression is the AI needs some significant tweaking on the easy level. Not to be Captain Obvious or Melvin McCranky Pants but easy should be... well easy. Its where you learn the ins and outs of the game play.

It just felt like a tremendous grind for each planet, endless enemy spawn, and never enough ships to plug the gaps no matter how many times I beat the incoming fleets

Oh and normal should be a challenge for the average player.

VulpesWalker

Newcomer

VulpesWalker

Newcomer

13 years ago

May 28, 2012, 12:16:05 AM

Nosferatiel wrote:
*tinkers a bit the summon dev spellbook, black candles, badly drawn pentagrams included, blood sacrifices and gore excluded*

I think the AI can cheat a little bit, if not it just has a better area to start out, but most of all... I must say I'm quoting that if I have your permission Nosferatiel (ex: Facebook and the likes)

a4nic8er

Senior Survivor

a4nic8er

Senior Survivor

21 900g2g pts

13 years ago

Jun 6, 2012, 9:22:17 AM

Some of the AI behaviour seems a bit suspicious to me.

Such as the way when, at first contact or immediately after declaring war, I probe an AI race with one or two small ships using kinetics, to see what they are using (i.e. mainly missile with a little kinetic), I send in a couple of large heavy fleets with plenty of flack & deflect armour with invasion mod and beam weapons. All is fine and I wipe out the defense fleet so fast that only 1 or 2 ships get their missiles off and I take almost no damage at all and have 2 full battle rounds to heal up. Very next turn, the enemy sends in 10 full fleets from an incredible distance away and the damage my laser weapons do drops from 50+% to less than 20% and both my fleets are wiped out. I mean, that AI was real quick to suddenly research shield defence, get massive movement bonus, have the dust to upgrade all those fleets and not miss a single turn of movement in getting them into my face.

I think the AI already cheats.

Mansen

Enthusiast

Mansen

Enthusiast

19 200g2g pts

13 years ago

Jun 6, 2012, 10:17:44 AM

isaristh wrote:
I'm going to hope the AI doesn't cheat, or at the very least an option is given to enable or disable cheats. Quite a few games in the past have really ticked me off when the AI gets handicaps and advantages, sometimes when they don't really need them. I can understand cheats on harder difficulties or something, but there needs to be an option where the AI is no better off than you are.

They're called restraints - designing a thinking AI is not something you just do. Especially not in games as complex as these. Sorry but you're going to have to live with some cheating.

metaspirit

Newcomer

metaspirit

Newcomer

13 years ago

Apr 29, 2012, 6:00:01 PM

must say this makes me chuckle

Originally Posted by Nosferatiel

I'm just curious if techniques I've seen used in physics actually have interesting other properties than searching for, let's say, the goddamn Higgs particle. XD

so i had to add this makes youre mind allmost exsplode

http://io9.com/5905897/the-webcomic-guide-to-the-higgs-boson

Becks

Newcomer

Becks

Newcomer

13 years ago

Apr 27, 2012, 10:36:39 PM

metaspirit wrote:
just as the title says will the ai cheat i blew the dust off moo2 and it struck me.

Just how much the ai cheats:eek: you know like 5-10 turns into a game and you meet another race and they already have 5 to 8 worlds. Its like they have x3 speed its just like fighting up hill so whats the ai going to be like ? anyone know

If I remember right, SpaceTroll said that "you can compare the AI to a baby. A complex brain but it doesn't know how to use it well." Therefore I think that the AI will not cheat.

The baby needs only some training.

MODNosferatiel

Informer

"God's in his heaven, all's right with the world." Nerv Motto, Neon Genesis Evangelion

MODNosferatiel

Informer

47 300g2g pts

13 years ago

Apr 27, 2012, 11:06:17 PM

*tinkers a bit the summon dev spellbook, black candles, badly drawn pentagrams included, blood sacrifices and gore excluded*

Just out of interest: Do you use some kind of multivariate approach for the AI like a "maximum likelihood of winning move" approach for each decision with some randomisation involved to not frustrate the player with a perfect game, neural networks, genetic algorithms or something I haven't named?

Or is it even easier and just randomisation + a really broad set of rules that cannot be breached, so the AI doesn't reach the zombie brain state?

I'm just curious if techniques I've seen used in physics actually have interesting other properties than searching for, let's say, the goddamn Higgs particle. XD

maceman

Newcomer

maceman

Newcomer

200g2g pts

13 years ago

Apr 28, 2012, 12:52:02 AM

yup...

story: excellent [x]

graphics: shiny [x]

races: sexy [x]

SP/MP: [x]

4X depth/replayability: ? []

AI: critical core element HAL [] aka the dumb blonde effect, "Wow she's HOT but dumb as rocks. I just can't see spending the rest of my life with her...."

isaristh

Newcomer

isaristh

Newcomer

13 years ago

Apr 28, 2012, 5:55:02 AM

I'm going to hope the AI doesn't cheat, or at the very least an option is given to enable or disable cheats. Quite a few games in the past have really ticked me off when the AI gets handicaps and advantages, sometimes when they don't really need them. I can understand cheats on harder difficulties or something, but there needs to be an option where the AI is no better off than you are.

MODVieuxChat

Chameleon

Truth is a chameleon. Herbert

MODVieuxChat

Chameleon

25 400g2g pts

13 years ago

Apr 28, 2012, 6:58:28 AM

Nosferatiel wrote:
*tinkers a bit the summon dev spellbook, black candles, badly drawn pentagrams included, blood sacrifices and gore excluded*

Just out of interest: Do you use some kind of multivariate approach for the AI like a "maximum likelihood of winning move" approach for each decision with some randomisation involved to not frustrate the player with a perfect game, neural networks, genetic algorithms or something I haven't named?

Or is it even easier and just randomisation + a really broad set of rules that cannot be breached, so the AI doesn't reach the zombie brain state?

I'm just curious if techniques I've seen used in physics actually have interesting other properties than searching for, let's say, the goddamn Higgs particle. XD

What I'd like is personnality. One Dumb AI, one that favors strongly attack, another that often tries to blackmail you, another one that favors peace, another one that favors exploration, etc.

MT4K

Newcomer

MT4K

Newcomer

13 years ago

Apr 28, 2012, 9:19:56 AM

I like to think that amplitude will also patch the a.i over time to use and counter player strategies.

VIPSharidann

Newcomer

VIPSharidann

Newcomer

16 500g2g pts

13 years ago

Apr 28, 2012, 8:12:01 PM

What I am convinced we will get is an AI which Acts in accordance to the Background of its faction... But Not stupidly. I.e. Cravers aggressive but Not right away, only After Getting a Chance to Evaluate the threat you Represent.

Xervitus

Newcomer

Xervitus

Newcomer

19 000g2g pts

13 years ago

Apr 29, 2012, 2:20:12 AM

I'd prefer more "racial picks" for an AI over outright cheating. All races are not equal...maybe different race stats could be another modifier in game setup.

metaspirit

Newcomer

metaspirit

Newcomer

13 years ago

Apr 27, 2012, 8:16:48 PM

just as the title says will the ai cheat i blew the dust off moo2

and it struck me.

Just how much the ai cheats:eek: you know like 5-10 turns into a game and you meet another race and they already have 5 to 8 worlds. Its like they have x3 speed its just like fighting up hill so whats the ai going to be like ? anyone know

White-Rabbit

Newcomer

White-Rabbit

Newcomer

6 000g2g pts

13 years ago

Apr 29, 2012, 10:56:08 PM

I hope the ai doesnt cheat i find it really anoying when they do. I guess it can behard to make an AI that works then make it work with different levels of skill with out resorting to handicapping or boosting its abilities. You could do a head start for the AI to add more dificulty (as an option) so they get 5,10 or 20 turns at beginning before you start. You coud say this is the same as cheating but its only temporary.

eleazzaar

Newcomer

eleazzaar

Newcomer

13 years ago

Apr 30, 2012, 4:28:02 AM

Usually developers of 4x games have only 2 realistic options:

1 let the AIs cheat

2 let the AIs be pushovers

No doubt theses guys would like to make an AI that didn't need to cheat, but they really won't know how good their AI is until after all the mechanics and relevant content are done.

maceman

Newcomer

maceman

Newcomer

200g2g pts

13 years ago

Apr 30, 2012, 5:51:47 AM

computer cheating i can deal with as they usually have some intrinsic vulnerability. now humans cheating... that's more irksome as they are usually healing over vulnerabilities.

DEVThorTillas

Dev

Florian - Lead programmer on Humankind

DEVThorTillas

Dev

30 200g2g pts

13 years ago

Apr 30, 2012, 12:34:51 PM

Hi there,

As long as I need to work, I cannot read all your posts… and unfortunately writing an answer takes me so much time that you guys are able to add 3 or 4 more posts before I’m done...

But this thread seems to be “the one” I need to follow it as long as a large part of my job at Amplitude is about AI development.

Will the AI cheat ?

-> Short answer : no.

In fact, the AIs will not gathered any information that a player cannot get and it will not be able to do actions that the player cannot perform.

But, depending on difficulty level, it will get some “Bonus” or “Malus” to his “Food/Industry/Science/Money” production.

The AIs have some difficulty to “always” make the right decisions in terms of system improvements or ship design creation. By giving them some production bonus, we allow them to make some little mistakes from time to time.

Did you use any neural network, genetic algorithms or any other research based algorithms?

-> Short answer : no

We don’t use Neural network or genetic algorithms. They are clearly difficult to canalize and are not applicable for our problems. But some other games have already used them. “Black and White” use a neural network as one part of the Creature AI and as far as I remember, “Creatures” use some genetic algorithms.

But it does not mean that we don’t use any architecture or concept from the research or previous games.

The large part of our architecture is based on automated agents. Like “Divide and Conquer”, we have split the whole AI in smaller parts named agents. Each agent is able to handle a specific task like the population repartition, choose a building to build, a ship design creation, the right tax rate to set, etc. The decision algorithm is based on input settings and world observation. The agent can change the world in his responsibility’s limits and send suggestions to other agents in order to get some help, change some other agents settings, etc.

When all the agents have done their jobs, several managers analyze the world and choose the agent’s settings for the next AI run.

Will the AI have personalities?

-> Short answer : yes

We build a personality settings in Endless Space. Each faction has its own personality and we can add some more, based on victory goals or the game’s current state.

Personality will not change the way the AI will choose a building or move his fleet, but change which building to privilege, how many ships to keep in defense when attacking, how diplomacy will impact on the attitude toward the other empire, etc.

So, yes, AIs will not react the same way to an aggressive colonization or a scout destruction depending on his personality.

But algorithms behind the scene are the same, it is more a matter of perception of the world than a complete behavior change. Which means that a Craver will still check its fleet’s power before attacking even when its “attack modifier” is very high and/or its “defense modifier” very low.

That said. I hope those explanations were clear and answered a part of your questions...

Cheers,

Florian (and Adrien who double-checked this over my shoulder ^^)

maceman

Newcomer

maceman

Newcomer

200g2g pts

13 years ago

Apr 30, 2012, 1:24:03 PM

And that folks is what makes this particular offering different. many thanks for the feedback Florian (and Adrien)!

Quick clarification. Will these same levels of AI automated agents be available for the human player? Can they be toggled on/off, make suggestions, or pop up with warnings of impending crises from around your empire?

MODVieuxChat

Chameleon

Truth is a chameleon. Herbert

MODVieuxChat

Chameleon

25 400g2g pts

13 years ago

Apr 30, 2012, 5:36:59 PM

I like the way those agents work. I'm curious to know more of them.

metaspirit

Newcomer

metaspirit

Newcomer

13 years ago

Apr 30, 2012, 5:57:49 PM

It's very nice to know that the ai will not cheat

It does look like the Ai will be very interesting with a modular design will be interesting to see how it will perform. can the Ai make changes to what's being built on the fly or does it make its decision and has to wait until it's built before changing it

Click here to login

Comment

Characters : 0