|
I'm sure a pretty strong bot could be made for Starcraft. However, the nature of the game would change when playing against that. Basically the human player needs to make a situation that the bot isn't programmed to handle and where the inhumane micro tricks don't matter.
Some things that seem difficult to program:
Anything in late game Defending against harassment Defending against multi-pronged attacks Base trades Using spellcaster units
To make an AI for Starcraft that would actually regularly beat the pros even after its gimmicks are figured out, would probably take almost as much effort as for Go, which has had lots of attention and huge projects dedicated to it since forever, yet the bots are still losing to Go professionals. Starcraft is a video game that keeps changing and will fade sooner or later, so no one's going to start long winded AI projects for it. Also just because of how the game is, the programming would be rather tedious and uninteresting.
It's possible in theory, but in practice we will most likely never see pro level bots for Starcraft.
|
IBM's Watson beat the two most accomplished Jeopardy players earlier this year.
|
If the computers were perfect, they'd be predictable wouldn't they? Isn't watching GSL fun because it's two human beings fighting against each other and trying to exploit each other's weaknesses? Where would the mind games be in computer vs computer?
|
On November 12 2012 10:21 InvXXVII wrote: If the computers were perfect, they'd be predictable wouldn't they? Isn't watching GSL fun because it's two human beings fighting against each other and trying to exploit each other's weaknesses? Where would the mind games be in computer vs computer? yeah, the 100m sprint is still insanely popular, doesnt matter if a car can do it faster, people want to watch humans do it. Sure drag racing is popular, but it didnt kill athletics
|
On November 12 2012 06:52 Scholera wrote:Show nested quote +On November 11 2012 12:56 Warlock40 wrote:On November 11 2012 12:53 AbideWithMe wrote: Perfect mechanics and micro with predefined build orders yes ofc.
Perfect strategies and scouting with dynmaic BOs not so much.
With certain pefectly executed timing pushes A.I. could beat every human for sure though. This. I could see Automaton 2000 having a ludicrously high win rate within the first ten minutes of the game by executing a marine timing attack with impossible micro. no, you could always fuck with it. For example: if you have a group of lings with higher mobility than their marines and threaten to counter attack, will they push to your base or try to defend?
Both, 20 marines perfectly microed stutter stepping around individual buildings to kill your entire ling army, 20 marins your base
|
On November 11 2012 14:34 Figgy wrote:Show nested quote +On November 11 2012 13:07 Ettick wrote: I mean it would probably take a while, but couldn't you program the AI to scout and build the correct units and buildings based on what they see, in addition to program it to have perfect macro and micro? Absolutely, 100% never. There is an impossible amount of variables to ever, ever take into account that an A.I. will simply never be able to handle. For example, protoss does a standard FFE and Zerg can't punish it. Zerg is either programmed to All In or get a 3rd hatch. Easy enough. What happens if the 3rd base is cannon rushed and the A.I. didn't scout it until it may or may not be too late to save. How does the A.I know what to do? Do you know how hard it is to program a response to something so simple that a human will be able to decide instantly just through practice? Do I let the hatch die? Do I build lings to save it? How many lings? Does it depend on the amount of cannons? What if my Zerglings get walled off AFTER they are already on the way or in production in a way that a computer cannot possibly forsee that makes it impossible to stop? Do they send the lings anyways? If I don't save it and I have no scouting information, how does the build proceed? What if I have zero scouting, when as a programmer do I set my A.I to rebuild that 3rd base with zero information? When do I build enough units to clear out the cannons? When is it plausable to take your 4th instead of the 3rd base location? Is it possible to make this move on every map? There are THOUSANDS of scenarios from the first 5 minutes of a game that can throw an A.I. off it's set pattern. Even the best of the best Chess computers don't determine their openings, they have a vast opening book with variations made by top GMs because the options early game are simply too vast for the computer to realistically figure it out. People can make these "Easy" decisions because of common sense. Computers can't.
Lol, the ai could calculate every possible unit comp it could produce and decide if it was worth it and from that point could decide if it needed to build a new base. Besides the ai wouldnt let itself get cannon rushed nor would it ever fail to account for a composition or sneak attack
|
It would be very interesting to see an AI developed, but as people have said it's far too large a project for people to be that invested into. Sort of why the blizzard one is so straight forward and the main discernable difference between levels of AI is how fast in undertaking a build order they are.
|
Would be nice to see a legit AI map in sc2 that can do this.
But atm their are only 3rd party hacking/botting programs that can do this, There are several of these out and will get you banned.
Few Hackers coding a .lua script bot to excute perfect splits/timming attacks ect ect and basicly can auto play ladder up to master league with all ins programed........so yes its possible, don't think blizzard would work on the AI anytime soon.
It's not exactly that possible in custom map creation, you would need 3rd party tools that would result in a ban.
There is only so much a map creator can do to tweak the AI with just the Editor blizzard provides.
|
it would so easy, just have the computer micro perfectly
|
On November 11 2012 14:34 Figgy wrote:Show nested quote +On November 11 2012 13:07 Ettick wrote: I mean it would probably take a while, but couldn't you program the AI to scout and build the correct units and buildings based on what they see, in addition to program it to have perfect macro and micro? Absolutely, 100% never. There is an impossible amount of variables to ever, ever take into account that an A.I. will simply never be able to handle. For example, protoss does a standard FFE and Zerg can't punish it. Zerg is either programmed to All In or get a 3rd hatch. Easy enough. What happens if the 3rd base is cannon rushed and the A.I. didn't scout it until it may or may not be too late to save. How does the A.I know what to do? Do you know how hard it is to program a response to something so simple that a human will be able to decide instantly just through practice? Do I let the hatch die? Do I build lings to save it? How many lings? Does it depend on the amount of cannons? What if my Zerglings get walled off AFTER they are already on the way or in production in a way that a computer cannot possibly forsee that makes it impossible to stop? Do they send the lings anyways? If I don't save it and I have no scouting information, how does the build proceed? What if I have zero scouting, when as a programmer do I set my A.I to rebuild that 3rd base with zero information? When do I build enough units to clear out the cannons? When is it plausable to take your 4th instead of the 3rd base location? Is it possible to make this move on every map? There are THOUSANDS of scenarios from the first 5 minutes of a game that can throw an A.I. off it's set pattern. Even the best of the best Chess computers don't determine their openings, they have a vast opening book with variations made by top GMs because the options early game are simply too vast for the computer to realistically figure it out. People can make these "Easy" decisions because of common sense. Computers can't.
I think you underestimate what cleverness and time can do, People made the exact same arguments about chess computers (computers could never hope to match human intuition) and look at the state of humans vs computers in chess now...
|
How does a AI beat a human on CS... that doesn't seem right I think no way in hell a bot team can beat teams like fnatic,ESC,Na'Vi.....
|
Edit: wops, double post. Sorry!
|
On November 12 2012 15:33 Severus_ wrote:How does a AI beat a human on CS... that doesn't seem right I think no way in hell a bot team can beat teams like fnatic,ESC,Na'Vi.....
Insane reaction time and aim?
|
On November 12 2012 15:33 Severus_ wrote:How does a AI beat a human on CS... that doesn't seem right I think no way in hell a bot team can beat teams like fnatic,ESC,Na'Vi..... I honestly hope you are joking, the Bot team would have 100% headshots, instantly as the player is visible. Basically, think aimbot. The only way a pro team would have a chance is if they grenade spammed the Bot team perfectly and killed them without being in a firefight.
|
On November 12 2012 11:12 vorxaw wrote:Show nested quote +On November 12 2012 06:52 Scholera wrote:On November 11 2012 12:56 Warlock40 wrote:On November 11 2012 12:53 AbideWithMe wrote: Perfect mechanics and micro with predefined build orders yes ofc.
Perfect strategies and scouting with dynmaic BOs not so much.
With certain pefectly executed timing pushes A.I. could beat every human for sure though. This. I could see Automaton 2000 having a ludicrously high win rate within the first ten minutes of the game by executing a marine timing attack with impossible micro. no, you could always fuck with it. For example: if you have a group of lings with higher mobility than their marines and threaten to counter attack, will they push to your base or try to defend? Both, 20 marines perfectly microed stutter stepping around individual buildings to kill your entire ling army, 20 marins your base
Keeping half the marines in their base wont work because you can simply run back to your own base at the last minute and they will have only half o their army against all of your army. That's the usefulness of high mobility.
|
|
It's the name of the first computer that beat a chess pro.
|
On November 12 2012 08:01 Fluid wrote: The brood war AIs are somewhere around master level (C- to C+), so they beat 95% of players already.
Not even close, the BW AI is a joke and any D- player wouldn't need more than 2 games to beat it (first game to see what it does since it does pretty much the same thing every time, second game to beat it).
On topic, I think it's very possible since perfect micro is already something that is doable by AI's, but it'd be a lot harder to make an AI that isn't too predictable, is very thorough with everything it does, scouting, building placement etc, and that doesn't just die to some random cheese. Hard, but possible.
|
United Kingdom14103 Posts
I'd just like to say thank you for this thread, one of the most interesting reads I've had in a while.
^As proven by me. BW AI is easy to deal with.
|
I'd love to see someone make a genetic algorithm for a SC2 AI and throw a bank of computers playing 24/7 at the problem.
|
|
|
|