*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

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...."

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.

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.

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

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.

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.

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

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.

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.

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.

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 ^^)

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?

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

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