Abraxis
☮
I'd rather see Firaxis hiring a couple of thousand Indians which are always on standby to play as the ai when you're playing the game.
lol!
this. this would be awesome.
I'd rather see Firaxis hiring a couple of thousand Indians which are always on standby to play as the ai when you're playing the game.
Part of intelligence is the ability to adapt and learn. I have yet to see a game with actual intelligence involved.
Love how AI is artificial INTELLIGENCE.
Part of intelligence is the ability to adapt and learn. I have yet to see a game with actual intelligence involved.
owned you there.
BTW. about learning AI i really believe it's the future of gaming too.
i once read an aticle about robots programmed with learning AI, and those robots were designed to keep a football match against other robots. 1 team had learning AI, the other team was normally programmed. The first few matches the programmed team owned the learning bots quite hard, untill the learning bots realised they shouldn't lose and they 'upgraded' their play and then they won nearly every time since then.
it will be fun to get learning AI in games, because then we can finaly get a non-cheating AI which will ALWAYS be a challange, and the most fun thing is that the AI will also find effective counters against 'overpowered' or 'overused' strategies.
if anyone keeps beating you using a really annoying strategy and you can find a counter yourself, try to copy the strategy as perfectly as possible and use it on the learning AI a few times. see ho it responds, and it will propbably beat you after a few tries. there you'l have your counter.
tho to be honest i think civ 6 will not get it, knowing how they never really care for common sence.
You are describing building a battleship when "all" that is needed is a fishing boat.The other concern is sheer computation needed. Learning AIs could theoretically figure out that when they do this stuff in civ, they tend to do better, but when they do that stuff in civ, they tend to do worse. They could - in principle - work out what they need to do. The problem is, they'll have figured it out by brute force or something like it; evaluating the current game state will take them vastly more time and processing power than an AI which has been built and optimized specifically to play civ. We're talking many orders of magnitude here; if it takes a minute to compute end of turn results for a handcrafted AI like they have now, it might takes years for a learning AI which has learned its way to the same level of proficiency.
You are describing building a battleship when "all" that is needed is a fishing boat.
There really is no need to use any overly complex, rigid and system demanding code (such as calculating all possible moves and outcomes several turns ahead). Sub-sectioned strategies/goals chosen from a default library of strategies/goals - combined with simple statistics of the outcomes gained from trial and error adoptations/pursuits of those strategies/goals under the given circumstances - would prove to offer quite an improvent over current AI performance (over time at least).
The AI could even have a central online database for such statistics for sharing (both ways) among the local AIs the world over - which would also be a valuable tool for AI coders for developing new default AI sub-sectioned strategies/goals.
There would of course have to be options to turn off the AI's ability to make use of what it has learned and only stick with the default defined strategies/goals (for the sake of casual and new players - as well as for competition use).
I don't think you quite got the drift of how the method I described would actually work. I am in fact not talking about methods to optimize the 'check-everything' procedure you think would be necessary.Only sort of. ...