Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

StarCraft AI Competition Results

Soulskill posted about 4 years ago | from the teaching-skynet-the-zerg-rush dept.

Programming 113

bgweber writes "The StarCraft AI Competition announced last year has come to a conclusion. The competition received 28 bot submissions from universities and teams all over the world. The winner of the competition was UC Berkeley's submission, which executed a novel mutalisk micromanagement strategy. During the conference, a man versus machine exhibition match was held between the top ranking bot and a former World Cyber Games competitor. While the expert player was capable of defeating the best bot, less experienced players were not as successful. Complete results, bot releases, and replays are available at the competition website."

Sorry! There are no comments related to the filter you selected.

I for one (3, Funny)

Anonymous Coward | about 4 years ago | (#33908120)

am terrified we're actively pursuing the ability for our robot overlords to have the perfect micromanagement strategies.

Re:I for one (1)

e4g4 (533831) | about 4 years ago | (#33908272)

Well - I'm not worried until the genetic engineers breed and train mutalisks for our robotic overlords to micromanage.

Re:I for one (4, Funny)

durrr (1316311) | about 4 years ago | (#33908464)

Overlords can be spawned from hatcheries, your real enemy is the robotic overmind. Know the difference, it could save your life.

Re:I for one (0)

Anonymous Coward | about 4 years ago | (#33908536)

We already have autonomous drones that can shoot and drop bombs, seems like we are there already.

Re:I for one (1)

atrain728 (1835698) | about 4 years ago | (#33908684)

Unmanned != autonomous

As far as I know, there are no deployed technologies that shoot [missles] or drop bombs without human intervention.

Re:I for one (1)

wickedskaman (1105337) | about 4 years ago | (#33909188)

Oooooooh! You just SERVED him!

Served! Served! Served! Served!

Re:I for one (1)

braeldiil (1349569) | about 4 years ago | (#33910190)

If configured to do so*, the Aegis weapon system can fire missiles at targets with no human intervention. Been that way since it first went into service. I don't think any fleet ship uses the capability, but it has has been baked in since the first ship. A CIWS gun in automatic will engage anything that appears to be a threat in its assigned area. *Proper configuration is firing keys in (to enable weapon launch) and Auto Special doctrines enabled. At that point, any track that matches the criteria will eat a missile, usually launching before the crew is aware there's a new threat.

Re:I for one (3, Funny)

darthdavid (835069) | about 4 years ago | (#33910370)

Yes but that's mounted on a warship, that mode can be turned off (by manually disconnecting the weapons if necessary, there are people on board after all) and that mode would only be turned on if a shooting war broke out and they needed to make sure that the ship wasn't going to get blown up before they could hit the "shoot down that motherfucking missile screaming in at us" button.

It all adds up to something a bit different than an autonomous weapons platform that can choose to engage targets at will, which is what other people were talking about.

Re:I for one (1)

damien_kane (519267) | about 4 years ago | (#33908810)

If they can't learn macro, though, then they won't have an We just have to make sure we don't teach them how to use/build their unit-producers.

Not equal (5, Insightful)

Pojut (1027544) | about 4 years ago | (#33908122)

By default, I'd say that a well-designed bot in an RTS would have an advantage over all but the best players. Since there is so much to keep track of, software would win out over wetware.

Bots in an FPS are one thing, but when you have dozens of units, a build order, multiple fronts, resources, and more to track all at the same time, the infinitely scalable multitasking of a bot would certainly come in handy.

Or maybe I'm off base?

Hello cum-guzzler (-1, Flamebait)

Anonymous Coward | about 4 years ago | (#33908166)

IMHO, SC2 is very good.

Re:Not equal (2, Insightful)

Alsn (911813) | about 4 years ago | (#33908198)

A bot would always be superior in multitasking, but the most important ability in Starcraft(which the article is about) is decision making which is really hard to program for an RTS bot. Or at least, so it would seem as I've never seen an RTS AI that hasn't cheated and at the same time been challenging.

It doesn't matter if you have the best multitasking in the world if the opponent can just outright kill you cause it has more stuff.

Re:Not equal (1)

durrr (1316311) | about 4 years ago | (#33908606)

Good multitasking can win even if you have more stuff. Kiting and withdrawal of units low in hp from battles can make a huge difference. SC2 reapers with some kiting and finesse can wipe out a much larger force, or simply outrun or avoid your troops while destroying your base. Combined with more troop types and activated abilities you can make a huge difference depending on micromanagement/multitasking capabilties.

Re:Not equal (2, Interesting)

immakiku (777365) | about 4 years ago | (#33908710)

Examples like that are rare. Taking your example of SC2, there's few scenarios where superior micromanagement can turn a big disadvantage. From experience, most silver+ level players do not just NOT micromanage their units. They just do it without taking a hit in their macromanagement or they do it less effectively than top level players. Even in the reaper vs ling/roach scenario, a player who's seen the situation more than once will know how to properly react (without needing to excessively waste APM defending against the reapers).

Re:Not equal (0)

Anonymous Coward | about 4 years ago | (#33911700)

What are you smoking? Gold/Diamond matches are chalk full of micromanagement in comparison to lower tiers. Its one of the things that separates pros from the rest of us.

I mean really the game has quite a few facets to it and you can't just ignore any of them:
  - Intelligence/Counter-Intelligence
  - Economy Development
  - Technology Development
  - Resource Management
  - Military Strategy
  - Military Tactics

I can definitely say in the hundreds of games I've played that once I got to the higher tier the first and last points became more important. The trick is you can't slack in any of the other departments so you have just more work to do. Its probably the only thing that keeps me playing the game given the way Blizzard has been acting lately. If it wasn't more entertaining and engaging than they are annoying I'd probably be boycotting them.

And by the way, APM is a stupid meter. Micro doesn't mean you click a million times (which is all APM is really recording). Micro is how much control on an individual unit basis you have, specifically compared to your opponent. I can flat out tell you that I've had dozens of games where after a set back from a clever opponent I was able to deal with a superior force simple by managing my micro better. Mind you, this won't save your 4 Mutalisks from a dozen Carriers but straight numbers is not the key to victory.

Of course, the best players don't *let* their opponents even bring anything heavy to bear...

Re:Not equal (3, Interesting)

Alsn (911813) | about 4 years ago | (#33908842)

Of course it can make a huge difference, but no matter how good your multitasking is, tanks still don't shoot up...

The point is, it's really easy to just outsmart an RTS AI once you figure out its tendencies. No matter how good it's multitasking is your own won't be bad enough that your flying units all of a sudden forget how to shoot down.

Having an intricate knowledge of counters and economy and timings(at least as far as starcraft goes) has always been superior to multitasking, but only to a point. There are things that you can take advantage of with near-perfect multitasking and control, but you need to actually know what to do with that control(and so far, no AIs do). A good example of what you can use AI for is in the article video demonstrating mutalisk/scourge control at a level which no human player would be able to accomplish. The only problem is that a human player would know that the AI is capable of that and just play around it.

An example would be some extremely mechanical starcraft players(NaDa, a korean progamer comes to mind) being able to just completely outdo their opponents with pure control and multitasking. The problem here though is that those players have such an immensely better understanding of the strategy and tactics of the game than a programmed AI can ever come close to even if it's not their strong suit(compared to other progamers who play more with smarts than raw hand speed). Their multitasking wasn't what won them games but rather a combination of their abilities. They still had far and away stronger decision making than your average player(or any kind of AI).

Re:Not equal (2, Insightful)

MoriaOrc (822758) | about 4 years ago | (#33912482)

Just to add on to your point. In the Mutalisk micro video, it's pretty clear that the mutalisks are prioritizing destroying siege tanks over goliaths. While that might be all well and good in some sort of base defense, or ground/air simultaneous attack, the videos are all of an air-only attack on the enemy base. The siege tanks are literally doing nothing but taking hits, while the goliaths represent the only actual threat to the Mutalisks (except the turrets in the final part of the video). Add on to that that IIRC goliaths take less damage to destroy then siege tanks.

Most human players would realize to attack goliaths before siege tanks in the same scenario, since they are both a softer target and a more immediate threat. Destroying them first means the Mutalisks could continue to harass the enemy base without taking any harassment back. However, the AI doesn't realize this and keeps attacking siege tanks whenever they are present.

Re:Not equal (1)

brkello (642429) | about 4 years ago | (#33908858)

This is true, but it doesn't matter how good your micro manage is if the units aren't in the right place. Simple drop strategies and resource starving are going to beat these types of bots.

Re:Not equal (1)

JTsyo (1338447) | about 4 years ago | (#33911082)

That's why the AI should always rush. This would reduce the possible counters the human player would have. Once there's a few units out, split them into 3 groups and harass the player (ie attack workers, supply, production). If the player comes with a superior force against one, retreat it. If he splits his forces, engage if it can win. Other than the top tier players, no one can handle microing 3 fronts while still keeping up with marco.

Re:Not equal (1, Informative)

Anonymous Coward | about 4 years ago | (#33908232)

you're not, and it's interesting that these Ai's only have as much knowledge of that game as a normal player would, no magic ESP or extra resources to make up for in efficiency. My favourite one was an AI that could play the game for you, but you as a human would give it overarching decisions, I couldnt find it on a quick google but there's a video of someone playing on youtube and I reckon it'd beat me hands-down.

Re:Not equal (5, Informative)

imgod2u (812837) | about 4 years ago | (#33908310)

It's a huge advantage but it's only one part of the game. Many would argue that overall strategy is far more important than micro-management.

One of the top protoss players (WhiteRa) in SC2 (former SC1 player) has a relatively low actions-per-minute (APM) count compared to most players. Yet he still comes out on top by a lot.

Being able to multitask and micro-manage is definitely an advantage but a far more important ability is being able to plan on the larger scale. I've never seen an AI capable of harassment techniques, guerrilla warfare and exercising map control. Multi-pronged attacks are also something that it should theoretically be great at but it never really tries.

Re:Not equal (1)

immakiku (777365) | about 4 years ago | (#33908730)

In addition, addition APM does not equate effective actions. You have to know which units to move where to maximize advantage. This is again something the computer will have a hard time doing.

Re:Not equal (0)

Anonymous Coward | about 4 years ago | (#33908856)

That's true. I have a very low APM, unfortunately, they are probably at an equally low EAPM. I haven't played any multiplayer because I know I suck. I love the game, but I'm not very good. I'd probably be lucky to have a double digit win percentage, and that would make me cringe. I can't even finish the single player on normal diff (close, but the last mission is kicking my a$$ with the alternate choices I made to see what the other effects would be in the research trees).

Re:Not equal (1)

timster (32400) | about 4 years ago | (#33909608)

My experience has been that SC2 matchmaking is pretty reasonable, and there are a TON of totally bad players out there to give n00bs like you and me a reasonable win percentage. So yeah, you'll be ranked super-low but your win percentage will probably be okay.

Re:Not equal (2, Interesting)

kaizokuace (1082079) | about 4 years ago | (#33908892)

I agree with you whole heartedly. I am a Go player, so I understand that strategy and intuition come in to play with this type of game where "war" is concerned. The most advanced Go programs can't defeat a low level player. Being able to look at the board as a whole and not a series of spaces seems to be beyond these AI. In Starcraft I would imagine that an AI can't plan ahead for the types of actions a human would take. Being able to micro manage and deal with skirmishes and build orders and such is just a mechanical action. Just the basics of combat. Placement, actions, and timing of such is what matters. Not just that you send out a group to attack but where and when matter in the whole of the match. Planning ahead, asserting influence, being creative. These are the abilities humans have over the AI.

Re:Not equal (1)

crossmr (957846) | about 4 years ago | (#33909218)

Multi-pronged attacks are also something that it should theoretically be great at but it never really tries.

Mostly because if standard AI did this, players would raise hell. No human can really keep up with 2 100% controlled and coordinated attacks. Mainly because we have to split our resources between them. The AI could realistically perfectly control 2 attacks with all the skill that a human player could devote to a single attack.

Even with all the hot keys in the world you still need to flip your view between the battles. AI doesn't have to do that. You still have to keep 2 different attacks straight in your head. the AI has no problem making space for both.

I don't think it's so much a function of not really trying so much as no one bothers because it would be incredibly cheap.

Re:Not equal (4, Interesting)

UnknownSoldier (67820) | about 4 years ago | (#33909704)

> No human can really keep up with 2 100% controlled and coordinated attacks. Mainly because we have to split our resources between them. The AI could realistically perfectly control 2 attacks with all the skill that a human player could devote to a single attack.

The biggest problem is the INTERFACE of the game. Let me know when I can create on-the-fly Picture-In-Picture overviews of the map in real-time, so I _actually_ can attack/defend on multiple fronts.

Sad to see RTSs really haven't changed in 20 years ;-(

Re:Not equal (0)

Anonymous Coward | about 4 years ago | (#33910052)

Supreme Commander supports both picture in picture views, and multiple monitor setups.

Re:Not equal (1)

gknoy (899301) | about 4 years ago | (#33910094)

Rrrrrreally. That sounds pretty cool, though I'd probably be as terrible at it as I am at Starcraft.

Re:Not equal (3, Interesting)

iluvcapra (782887) | about 4 years ago | (#33910662)

The biggest problem is the INTERFACE of the game. Let me know when I can create on-the-fly Picture-In-Picture overviews of the map in real-time, so I _actually_ can attack/defend on multiple fronts.

An interesting modification to StarCraft which would give AIs a run for their money would be cooperative play where several users operate one team on the field, and where the several users have a hierarchy and delegate command of corps of units to other players, maybe one player handling resources while another scouts while a third consolidates the offensive force.

Re:Not equal (3, Informative)

Anonymous Coward | about 4 years ago | (#33911066)

Not "would" - does. That feature has been in the original StarCraft ever since. The original Age of Empires had that feature, too.

It's sad that they didn't include this in SC2 though.

Re:Not equal (1)

JTsyo (1338447) | about 4 years ago | (#33911152)

This is already possible in SC. You can have teams command just one "player".

Re:Not equal (3, Informative)

aeroelastic (840614) | about 4 years ago | (#33911968)

An interesting modification to StarCraft which would give AIs a run for their money would be cooperative play where several users operate one team on the field, and where the several users have a hierarchy and delegate command of corps of units to other players, maybe one player handling resources while another scouts while a third consolidates the offensive force.

This is basically what we would do in 4 v 4 Age of Empires. The person farthest from the other team would be "resource bitch". They would focus on tech upgrades to mining and farming, and be responsible for constantly supplying the other players with food, stone, etc. The other players would have no economy but would build cavalry, siege weapons, etc based upon what tech their civilization was best at.

Re:Not equal (1)

Pulzar (81031) | about 4 years ago | (#33912548)

Mostly because if standard AI did this, players would raise hell. No human can really keep up with 2 100% controlled and coordinated attacks. Mainly because we have to split our resources between them. The AI could realistically perfectly control 2 attacks with all the skill that a human player could devote to a single attack.

The great equalizer is that the computer would be leading half of his army to each attack, which would lead to annihilation of one of his two groups. Depending on what damage to the base(s) the other attack did, the computer army now has to deal with human army almost twice its size and would probably lose the game.

Multi-prong attacks are a good harassment strategy, but you can't actually win the war (not in SC2, anyway) by splitting your army in two.

Re:Not equal (1)

guruevi (827432) | about 4 years ago | (#33910698)

A lot of it is imho putting the human player on guard, playing mind games and making the other player think that you have more than you actually etc. something that most bots are inherently immune to. Intelligence and demoralization beats brute force most of the time in human warfare. Especially in electronic war games you can easily sacrifice a couple (or even a whole lot) of units in order to take the majority of the army out of position.

Look at Iraq for an example, there was bunches of brute force, the US could have just bombed (even non-nuclear) the whole country but they lost anyways because the other side outsmarted them (have squadrons looking through the desert and wasteland for a couple of nobodies among the rocks) and demoralized the supporters of the wars.

Re:Not equal (0)

Anonymous Coward | about 4 years ago | (#33912368)

Um, when did the US lose the Iraq war? Last time I check the US installed government in Iraq is still there.

Re:Not equal (5, Interesting)

Monkeedude1212 (1560403) | about 4 years ago | (#33908330)

Bots in FPS ARE a completely different thing, as setting up an auto-headshot sniper that will hit the player before he can get the bot into view is not that difficult to make. That field will never be an even battle.

Strategy games are a little different though. A Bot essentially has no "better" way to evaluate the player than any other player would evaluate the player. Say in Starcraft, the Bot scouts the player - and determines he is a little behind in what he would expect the player's army count to be. This could mean a number of things: The player made a mistake, the player is saving up, or theres something the player has that you have not found yet. How do you proceed?

Now - when you get to the pro level of gaming, you worry a little less about your opponent's build and worry more about not letting them know yours. Walling and other defensive techniques become just as important as scouting your opponent. The game becomes highly a higly reactive scenario as opposed to proactive. If you know what your opponent is doing, you can counter it and that puts you much further ahead, possibly ahead enough to crush them.

So the problem eventually lies in getting an AI to properly counter a players actions. Making an AI react to players is much harder than giving an AI a plan and telling him to execute. Because essentially the reaction is only as smart as whoever is programming the AI. And if you are a better player, capable of keeping other people from determining your plan, you can beat an AI who is trying to determine yours.

Don't get me wrong, the ability for computers to instantly Micro and Macromanage all of the units and resources at once does give it some serious advantages, but deep in the heart of it: The AI will only be a little better of a player than the person who programs him. (Or her, if you program female AI's like GLaDOS)

Re:Not equal (0)

Anonymous Coward | about 4 years ago | (#33908994)

Except for one thing. The bot is not affect by fog of war. I know this because I've seen the Terran scan pop up directly on top of Protoss observers when there were no Terran units close enough to know it was there. The AI knows where everything is at all times, and only mimics scouting actions.

Re:Not equal (2, Informative)

leonardluen (211265) | about 4 years ago | (#33909712)

as part of the rules for this contest the AI had to have fog of war turned on.

Re:Not equal (4, Funny)

Arancaytar (966377) | about 4 years ago | (#33909956)

Or her, if you program female AI's like GLaDOS

You will be Zergrushed. And then there will be cake.

Re:Not equal (0)

Anonymous Coward | about 4 years ago | (#33912266)

You will be Zergrushed. And then there will be cake.

The cake is a lie!

Re:Not equal (0)

Anonymous Coward | about 4 years ago | (#33910178)

Of course the performance is not equal in your comparison, because the challenges are not equal.

Most FPS bots cheat past the task of visual recognition, instead making use of perfect information about the opponent and the environment. When FPS bots have to play on equal footing with skilled humans, the bots lose. I mean, if I am playing against a bot, and I know that the bot is camped up there with a sniper rifle...I lob a grenade around the corner, BOOM! (no headshot necessary). It seems you are comparing FPS bots (cheating with the aid of perfect information) to RTS bots (playing on equal footing with humans, both coping with Fog of War).

Re:Not equal (1)

Monkeedude1212 (1560403) | about 4 years ago | (#33911470)

Bots still tend to outplay in that they have instant communication amongst other bots (Like the voice chat) and have quicker reaction times.

Even "on Equal Footing" Bots tend to play better, the only time they don't is when you purposefully detriment their regular abilities like accuracy and detection. Essentially if you and a bot were walking near each other, just a grenade lob away, the bot would be able to instantly know you are there because the instant the sound is registered in their detection range they can tell where your location is better than a human trying to generalize with their imperfect 5.1 audio setup and they don't have the split second reaction time involved.

Simply put, the computer is just plain faster at everything else, which in FPS is the main difference between winning and losing - twitch reflexes.

Re:Not equal (2, Insightful)

bytestorm (1296659) | about 4 years ago | (#33908346)

Ideally, you can watch your opponents prior matches and tailor your strategy to defeating him. A computer might have a harder time doing that, but a person would be able to recognize the weaknesses of a strategy on the spot. Starcraft is very much rock-paper-scissors.

Re:Not equal (2, Insightful)

e4g4 (533831) | about 4 years ago | (#33908682)

Starcraft is only rock-paper-scissors if you don't scout.

Re:Not equal (1)

damien_kane (519267) | about 4 years ago | (#33908864)

Starcraft is only rock-paper-scissors if you don't scout.

It's still RPS even if you do scout, the only difference being that if you scout, you know the player will choose rock, so you know to choose paper.
Essentially the, it's rock-paper-scissors-lizard-spock-zergling-zealot-marine-mutalisk-archon-[...]

Re:Not equal (1)

e4g4 (533831) | about 4 years ago | (#33909176)

Except that in Starcraft, you can kite your scissors (and other micro) and still beat rock.

Re:Not equal (1)

brkello (642429) | about 4 years ago | (#33908876)

Uh, you scout and realize they have paper so you build scissors. What are you talking about?

Re:Not equal (1)

KarrdeSW (996917) | about 4 years ago | (#33908414)

This would be true for initial battles against that AI, but at some point, the human player will come to understand the AI's tricks, which will always be finite. Even if the AI is sophisticated enough to change strategies when faced with possible defeat, it would be entirely possible for a human player to learn how to stay "on the threshold" so-to-speak and simply overrun the AI at the right time.

Knowing the AI's strategic plan is ultimately more important than being able to micromanage with more efficiency, IMO. Of course, you could make a game that requires excessive amounts of micromanagement intrinsically in order to be properly played, but then I don't think many humans would buy it anyway.

AI strategy (1)

Baron_Yam (643147) | about 4 years ago | (#33908848)

I've seen a lot of AIs that have a general strategy that they stick to like glue. I'd love to see an AI that continually evaluates its current position, and if it sees a loss trend, switches tactics.

When you're doing the right thing, but slowly bleeding out to inevitable death, you might want to lower your risk aversion and try something else.

Beyond that, some way of evaluating a player and keeping track over multiple games - and comparing known players and their styles to new players to make predictions, would be nifty.

Bots lack creativity (playbook-limited) (1)

rs1n (1867908) | about 4 years ago | (#33908814)

While a bot will certainly be able to macro and micro better than a human, human players are closing the gap and I don't think that the current gap is all that much between humans and machines.

On the other hand, the creativity gap between humans and machines is always in the favor of humans. At best (as of now), machines can only be designed to react, and their "creativity" is limited to a book of plays. Once you know the machine's playbook, you can easily defeat them. So they are only as good as how well their playbooks can be kept secret. Their ability to make a gamble during the heat of the battle (be it in attacks, build switching, etc) is still limited compared to humans (in my opinion). And this is often where tides turn in such games.

Re:Not equal (1)

brkello (642429) | about 4 years ago | (#33908834)

I disagree. Starcraft 2 has a lot of different strategies to account for. Sure, the bot should do a better job of being able to micromanage, build efficiently, not screw up on food, etc but a decent human will beat it because it will struggle to account for tricks that a human can come up with. A good human will implement its strategy on the fly. They will scout, see what the bot has and develop a counter. It has a big army? Do some drops in the back of their base. And usually a bot will have a flaw...a weakness it doesn't handle well. Humans are very good at figuring that out.
SC2 is just too complex and there are too many strategies. The harder AI in the game has to cheat to keep up with a human. The simpler the game, the easier it is for AI to win. The more complex it gets, the more it favors humans (well, at least games that are designed for humans...I could design a game for a computer to play that was extremely complex but required parallel actions to be taken very quickly and a human wouldn't have a chance).

Re:Not equal (1)

snadrus (930168) | about 4 years ago | (#33908986)

I've found that strategy in SC2 also. A few early invisible guys slip to the back of their base and kill off the workers, then it's over. They don't often realize it happened, they attack with their remaining army, and they freeze.
On the other hand, the SC2 AI is great if it should always on the offensive. My team has been hit with coordinated attacks that prevent us helping each other, especially when they run away.

Re:Not equal (1)

JTsyo (1338447) | about 4 years ago | (#33911230)

But usually the human will lose a game or two before he figures out the weakness. If the AI is programmed with 4or5 styles, it might be harder to figure out the counter. The AI still could have a fundamental flaw you can exploit but as long as you can adjust the AI you can reduces it's weaknesses with experience.

Re:Not equal (1)

immakiku (777365) | about 4 years ago | (#33908870)

Your idea is correct, but the use of the word infinite is off-base. That's like saying chess is infinitely variable. It's simply not true. There's only a small number of openers in both games. And from any situation, there's only a small set of viable next moves (somewhat true in chess - especially true in SC where the game flow depends heavily on what happened before).

In the beginning two minutes of the game, if you have more than 40 APM you're just doing something excessive. Even through midgame, until you're in the active engagement phase, 150 APM is more than sufficient for the number of useful actions you can take.

Re:Not equal (0)

Anonymous Coward | about 4 years ago | (#33909586)

While a computer is going to master the "macromanagement" of base-building, and following a predetermined course of actions to achieve the result, most of this is still well within the realm of human capability (although "perfect play" is only going to be achieved at the highest levels and only in the initial phases of the game).

Once you've gotten past the initial phase of economy building, where both a top human player and a well-designed bot are going to be neck-in-neck, it becomes a game of judgement and strategy, and it becomes another depth problem where 99.999999% of the available decisions suck, and a human player is still going to achieve better quick judgement calls.

Cool. (0)

Anonymous Coward | about 4 years ago | (#33908162)


Now someone write me a bot which helps me track down those bastard P'toss players who keep tower rushing the outside of my base, so I can teleport my fist in their respective faces.

lol, captcha: crystal.

Important note (4, Informative)

Monkeedude1212 (1560403) | about 4 years ago | (#33908170)

Uses Broodwar, not Starcraft 2, and not just the original.

Just saying. (Cause when they mentioned Ultralisk Microing, I thought about SC2 and how Ultralisks are terrible units there simply because they block your units making Micro a huge pain, and it wasn't so bad in BW when your units could take a bit more of a beating).

Re:Important note (0)

Anonymous Coward | about 4 years ago | (#33908254)

Lol you're clearly not much of a SC2 player if you think ultralisks are "terrible units" ... perhaps you'd like to argue your point with FruitDealer (winner of the first SC2 GSL tournament) who used them repeatedly to devastating effect.

Re:Important note (1)

Shados (741919) | about 4 years ago | (#33908558)

And you probably can count how many times he did after 1.1.1 patch on one hand =P

Re:Important note (1)

Vaphell (1489021) | about 4 years ago | (#33908614)

FruitDealer dominated his games from start to end, ultras were an icing on the cake. The truth is they offer much less bang for the buck than they used to in sc1. They have splash damage, but they are so huge now and that makes them a pain to micro effectively. They don't really synergize with other zerg stuff. Remember ultraling+dark swarm?

SC has good bots (0)

Anonymous Coward | about 4 years ago | (#33908196)

As a casual player of SC & SC2, I've always found the bots to be pretty competent and provide a decent challenge. There are some tricks to halt the AI early game but ignoring them and playing normally they provide a decent challenge. There's only been a few times it flakes out early game and doesn't climb the tech tree, usually happened with Zerg.

When I was a new player with SC I actually thought the bots were utterly brutal and was a little annoyed with no difficulty setting. After awhile I got used to how the game essentially threw you in the deep end and was able to fend for myself.

Re:SC has good bots (1)

am 2k (217885) | about 4 years ago | (#33908366)

After a while the AI in sc1 is dead simple to beat. It likes to send in units into your base at the same spot one at a time. Just place some static defenses there, and you can macro without being disturbed, and then when you're maxed run over it.

Now the sc2 AI is much better, I still have troubles coping with it in certain situations (esp early rushes) starting at the "Very Hard" difficulty. It doesn't wall off its base though, so sending in 50 speedlings can kill its economy early on, which causes it to never recover.

Re:SC has good bots (1)

zach_the_lizard (1317619) | about 4 years ago | (#33908576)

I'm really bad at SC2 online, but I never found the bots to be too bad, even at the higher difficulties. IIRC (it's been over a month since I played) they are really bad at defending against rushes.

Re:SC has good bots (1)

immakiku (777365) | about 4 years ago | (#33908804)

Try vs. Very Hard. Any decent rush strategy (that's not all-in) will be met with a good defense. The thing with the computer at VH level is it's a very balanced player. It builds units as it builds economy and tech tree, so it's hard to work a non-all-in rush against it, but it's fairly simple to out play it in either units or economy or tech and exploit the hole in its gameplay.

my 2 cents (0)

Anonymous Coward | about 4 years ago | (#33908250)

machine is capable of reading and executing way more instructions per sec than a human can ever do, however the difficulty is deciding which instructions it should execute, thats always the hard part with writing an AI. Writing a very good reactive bot is not an easy thing to do, because people can be unpredictable. my 1st ever /. post!

Re:my 2 cents (2)

grimJester (890090) | about 4 years ago | (#33908358)

When you play a game yourself, you only have to come up with a counter strategy to what your opponent is doing. When you program a bot, you have to think of all the possible strategies to counter and find reliable ways to recognize them in addition to having the counter.

Re:my 2 cents (1)

MadKeithV (102058) | about 4 years ago | (#33908830)

Or you have to think up a way to analyze any strategy generically and come up with a possible counter.

Re:my 2 cents (1)

Lehk228 (705449) | about 4 years ago | (#33909202)

I'd set up a genetic algorithm bot and turn it loose on battle net with 10 or 20 accounts until it was the best.

That's the best strategy? (3, Interesting)

jandrese (485) | about 4 years ago | (#33908302)

So the winner is just a Muta harassment bot? I have to wonder if the top level human player just spammed some Corsairs or Valks? It didn't seem like the AI was particularly good at changing strategy if the opponent countered. Spreading out the Mutas would help against a Corsair or Valk counter though, since both of those units rely on the Mutas natural tendency to clump to get maximum effectiveness.

Re:That's the best strategy? (2, Interesting)

Anonymous Coward | about 4 years ago | (#33908734)

Against Muta's? Just spam Goliaths.

Re:That's the best strategy? (4, Informative)

jandrese (485) | about 4 years ago | (#33909144)

The bot looked like it was pretty good at dancing the mutas around cliffs though, which is usually the downfall of Goliath spam.

Re:That's the best strategy? (3, Informative)

teko_teko (653164) | about 4 years ago | (#33909818)

It's actually pretty interesting technique that they used. They don't just clump up the mutas. From the results page:

Contemporary StarCraft wisdom tells us that the best way to use mutalisks is to clump them. In human versus human battles, this makes it difficult to single out the weaker mutalisks, because the units are stacked on top of each other. However, UC Berkeley’s team identified a flaw in this tactic; it reduces the damage output of each individual mutalisk, because not all mutalisks will fire when using this tactic. Instead, they employed a model in which mutalisk are always moving, maximizing damage output while simultaneously maximizing movement.

Video can be found at the bottom of the page [] .

Any 'learning' bots? (3, Interesting)

JSBiff (87824) | about 4 years ago | (#33908594)

Anyone know if anyone has ever created a bot that has the ability to learn from losses and wins, to figure out what works and what doesn't (both what it is doing and what the enemy is doing, then use that in the future to predict what the other player is *trying* to do and come up with a counter)?

I've not played a lot of RTS's, but I've played a few, and the thing I've noticed is, if a strategy works against a bot, even if there's a fairly obvious counter, it will always work against that bot.

The RTS I've played the most is Supreme Commander: Forged Alliance, so I'll use an example from that: There are a collection of different bots available which will use different strategies. Now, the player can build a strategic missile launcher, which builds nukes. You can also build a strategic missile defense which will build 'seeker' missiles which will shoot down incoming nukes.

Some of the bots will build SMD's, some won't, but in no case does it build an SMD based upon the player/opponent's actions. That is, it doesn't check to see if you have started to build any Strategic Missile Launchers before it begins to build the defenses. The bots that don't build defenses won't build them even if you are building one. This means on the one hand that the bot wastes resources which it could have used otherwise, to build defenses, while on the other hand, if it doesn't build them, you can pretty easily and quickly defeat the bot with a nuke or two. Alternatively, instead of building a strategic missile defense, the bot *could* try to use someattack method (for example, if you don't have good air defenses, it could hypothetically try a targeted attack with a bunch of bombers or gunships to either destroy the SML, or the engineer units which are constructing the SML).

However, the bots never seem to be smart enough to attack the obvious threat of a strategic missile launcher. It seems like the only way the developers found to make the bots harder is to make them much more efficient at building up their economy and spamming out lots of land-units to try to attack the player.

When I get a chance, I want to try SC2, but right now, I'm in a period where I'm not playing games as much as I used to, and trying to reduce my gaming down to almost none while I get some more important things done in RL. It'll be interesting to see how the AI differs in that game.

Re:Any 'learning' bots? (0)

Anonymous Coward | about 4 years ago | (#33908970)

Pretty much the same limitation, but smarter about it. The computer will scout you and build based on what it sees, but at the same time I can 4gate (build 4 unit producing facilities at the start of the game) and overrun the ai FAR easier than any reasonably skilled human opponent. A human might potentially build a bunch of canons or other static defense, the ai..never has. It's also pretty easy to exploit the stupidity of the AI by forcing a base trade situation - Get a reasonable number of units that are good against buildings and park them somewhere out of the way near the enemy base and then wait for them to move their army to your base. You can kill a good half their base as they decide to walk all the way back across the map to defend, when really they could have won if they just kept pushing and killed your base instead.

Weakness in strategy like that will always be exploitable. All you can really do is add enough different branches that its hard to predict what the AI is going to do, which is kind of how its like playing against a human. Even then if you force some early game confrontation, you limit the options they can do..again, also like a human.

If you want to get into sc2, I recommend watching the video series Day[9] Dailies on He started them back in the beta, where he would just have a topic for a show like "Reaper rushes" or "Heavy terran mech play" and he'll go through a few replays showing examples and explaining the differences in different related strategies, why some would fail and others wouldnt.

Also good is HDStarcraft and HuskyStarcraft on youtube. They don't explain so much, but they commentate a lot of great games that are fun to watch. I know plenty of people that watch these videos FAR more than they play, as its really entertaining and takes a lot less involvement than trying to do good in a ladder match

Re:Any 'learning' bots? (4, Funny)

Dakman (824764) | about 4 years ago | (#33909838)

A bot that learns from loses? An interesting game. It seems the only winning move is to be Korean.

Re:Any 'learning' bots? (1)

dorianh49 (988940) | about 4 years ago | (#33909908)

It's just a matter of getting the bot to play tic-tac-toe against itself. Unfortunately, it may not see the point of engaging in any "war" games after that.

Re:Any 'learning' bots? (0)

Anonymous Coward | about 4 years ago | (#33909958)

The older Command and Conquer games had adaptive AI. Even on the easy settings if you used a single strategy it would learn to counter. I know this was true for Tiberium Sun, at least, don't know about the other games in the C&C universe.

Re:Any 'learning' bots? (1)

jlf278 (1022347) | about 4 years ago | (#33910066)

Plenty of bots learn as they go. Some simpler ones might learn the layout of a level (counterstrike) or a room (roomba) through trial and error. You can imagine it would not be that hard to create a simple database that maps the geometry of such spaces to a reasonable resolution. Similarly, you could create a database of tactics in Starcraft for openings to easily identify the most effective ones all else being equal. Unfortunately, it could be difficult in a Player vs AI situation to gain enough high-quality data. Some AI's make use of AI vs. AI gaming to analyze effectiveness of different strategies, but obviously that will just make the AI's next build neccessarily better at playing against their current version. Obviously that's a big challenge.

Another huge problem is deciding how much an AI should imitate human behavior. In chess, it only matters that an AI wins. However, in video games, AI's are often ridiculed for not behaving like a real person: they use information not available to players, they violate the limits of what is possible for a human player to do, or even alter gameplay such that their units attack faster or are invincible to certain attacks. The programmers write the AI this way because they may have serious flaws or holes in their logic. AI's are almost always really lopsided in their competence at various aspects of play. Programmers often must max out an AI's strengths to compensate or the pathetic maximum of its weaknesses. Using a learning, dynamic AI would not neccessarily solve this problem. A simple example: in a fighting game like Soul Calibur, you could make the AI aggressively rush the human player at the beginning of the match. The second round, if this works, you could try it again. However, it turned out poorly, you could have the AI take a defensive stance next time around. This is a simple form of learning, but would be quickly obvious to the human player, who could then easily take advantage. A dynamic AI may be less predictable, but probably still somewhat predictable. It may not succumb to the same attack everytime, only to succumb too easily to various attacks. Also, you can add in some randomness to decrease predictability, but the AI will then be less productive.

Re:Any 'learning' bots? (1)

kodomo (1100141) | about 4 years ago | (#33912102)

that's not a good idea, everybody knows what would happen if you try it.

Are there bot v. bot competitions in SC? (1)

Dr. Spork (142693) | about 4 years ago | (#33909010)

There are software competitions in chess, and they're getting pretty exciting now that the software can play at a grandmaster level. I think it would be pretty cool if this sort of thing made it into games like Starcraft. In any case, I'm happy that bots and their authors are getting some prizes and recognition, because I think their work is incredibly important and fertile. Bots are out future.

Re:Are there bot v. bot competitions in SC? (1)

sagematt (1251956) | about 4 years ago | (#33909364)

In any case, I'm happy that bots and their authors are getting some prizes and recognition, because I think their work is incredibly important and fertile. Bots are out future.

I, for one, welcome our new bot overlords.

Re:Are there bot v. bot competitions in SC? (1)

JTsyo (1338447) | about 4 years ago | (#33911312)

There are no prizes, it's a lie. They do get the recognition. Maybe some developer would be interested in using a variant of their bot for a game.

Nerd Fantasy Extrodinaire: Ingame Scripting Agent (4, Insightful)

Wrath0fb0b (302444) | about 4 years ago | (#33909186)

Competitions like these are great, but they (and games like SCII) really make me pine for an RTS with a robust in-game scripting language. I would like to write complex auto-executing instructions for my units like "Pursue but never enter the firing zone of a known enemy turret or siege tank" or "If your energy > X and enemy of type Y in range R, cast spell S" or "If you are unit type X, always position yourself between friendly unit type Y and the enemy". You could confine the script to some reasonable specifications (say, no more than 1000 queries and 100 orders given per second) if you want to deter brute-force approaches.

This is a totally different problem than writing a good AI, you would be focused on writing powerful tools that aid, not replace, a human player by letting him specify his intent on a higher level than "go here" or "attack that". Better visualization of what's happening would be an integral part of this too. I would love to have SCII give me an overview of what units/building I have, what they are doing/queued to do -- even better if they are grouped into functional 'squadrons'. Being able to have multiple panes/monitors looking at different things would help to.

I guess what I'm saying is that I'm old and slow and want to leverage my experience writing rule-based logic to beat the whippersnappers that can click faster than I can and keep more things going in their heads at once :-P.

Re:Nerd Fantasy Extrodinaire: Ingame Scripting Age (0)

Anonymous Coward | about 4 years ago | (#33909592)

Taken to the logical extreme, it sounds like you just want a game where you don't have to micro your units.
(Assume you write the script, publish it, and the community picks from a set of micro scripts)

SC2 would then devolve into "I think he's going strategy Y, computer deploy counter strategy Y-c".

Which then devolves into "the AI deploys strategy Y-c because it is the most effective strategy against the observed strategy Y"

Which then devolves into Progress Quest.

Re:Nerd Fantasy Extrodinaire: Ingame Scripting Age (1)

shish (588640) | about 4 years ago | (#33911600)

Taken to the logical extreme, it sounds like you just want a game where you don't have to micro your units.

Actually, I think the extreme is a game where you write the script then you don't manage your units at all -- and it turns out that games like that are pretty awesome [] even when you only have one unit to manage, so I can only imagine managing a whole army would be much more fun (presuming the complexity wasn't overwhelming)

Re:Nerd Fantasy Extrodinaire: Ingame Scripting Age (0)

Anonymous Coward | about 4 years ago | (#33909866)


I remember thinking something like this when I played Mechwarriors; HOW COOL would it be if your Mech had an API and you could program or customize behavior?
In fact, now I want a Mech simulator that gives you generic programmable parts, and you can build your mech from scratch programming things like the gyro, actuators and so on.

Or maybe I should just get into electrical engineering and/or robotics and/or lay off coffee forever.

Re:Nerd Fantasy Extrodinaire: Ingame Scripting Age (1)

Asgaard (887693) | about 4 years ago | (#33909994)

That was me BTW.

For instance, imagine you're given a set of parts with simulated physics and physical+logical interconnects.
I figure with real robots there would be a lot of welding and metal-piece-shaping involved, but imagine if somehow all that was virtual/programmable, and the whole thing moved according to your programming (lower leg goes up to xx degrees, has such and such torque/force/movement curve). .... we could have competitions to see who can program the fastest running bot!



Re:Nerd Fantasy Extrodinaire: Ingame Scripting Age (0)

Anonymous Coward | about 4 years ago | (#33909874)

You should look at the Spring engine. I'm pretty sure unit behaviors can be scripted using things like Lua.

Re:Nerd Fantasy Extrodinaire: Ingame Scripting Age (1)

m50d (797211) | about 4 years ago | (#33910012)

A group of my friends have been working (slowly) on such a project for a while now. Though it's pretty much ended up being a client-server RTS where everyone writes their own client.

Re:Nerd Fantasy Extrodinaire: Ingame Scripting Age (4, Interesting)

ThePyro (645161) | about 4 years ago | (#33910328)

Have a look at the Spring Engine [] if you haven't already. There are a variety of RTS games, including some high-quality variants of Total Annihilation, which use the Spring Engine and allow for all sorts of client-side scripting through Lua. There are a variety of client-side lua "gadgets" that players have written already. You can move your units into custom formations by drawing lines or squiggles with the mouse; there are widgets to automate using air transports to ferry units between factories and rally points; there are even widgets to automatically alert the player when certain dangerous units are spotted. IIRC, someone was even working on a script for kiting with long-range units.

Re:Nerd Fantasy Extrodinaire: Ingame Scripting Age (1)

Jainith (153344) | about 4 years ago | (#33910604)

I kinda liked the "less control" approch of Majesty.

Your units actually think for themselves, and respond differently to your "reward" incentives. To me this makes for a more "realistic" experince than the "hive mind" approach of the standard RTS (Where the player controls exactly what every unit does.)

Re:Nerd Fantasy Extrodinaire: Ingame Scripting Age (0)

Anonymous Coward | about 4 years ago | (#33911548)

whilst the game is a simplification of what you're after, gratuitous space battles is a game entirely on this concept, you set up your units beforehand and then leave them to do their battle.

Re:Nerd Fantasy Extrodinaire: Ingame Scripting Age (1)

Salamande (461392) | about 4 years ago | (#33912358)

Did you ever play Carnage Heart [] ? It sounds a lot like what you're thinking of, though this was from the mid- to late-90s. My friends and I played this all through college. We eventually came up with some pretty ridiculous strategies.

Re:Nerd Fantasy Extrodinaire: Ingame Scripting Age (1)

islisis (589694) | about 4 years ago | (#33912576)

I'm glad to see a potential player base for this type of RTS. I would also love the ability to select from scripted build orders. Just let me fine tune bits of my second-nature strategies in game and let me concentrate on scouting and such.

Several non-obvious flaws (5, Informative)

Myji Humoz (1535565) | about 4 years ago | (#33909308)

There seems to be a very wide range in the abilities of the winner and runner up bots that might not be noticed by someone unfamiliar with Starcraft. In order of appearance:

1) In the flying units versus flying units match, mutalisks (guys with wings) should have focused the scourges (little 'c' shaped guys) because scourges have about 1/5th the health of a mutalisk, but can suicide to take out 5/6ths of a mutalisk's health. Red ai focused scourges, the other ai didn't, with disastrous results for the other ai.

2) In the match with infantry, the players had medics, which heal other units but can't attack, and marines/ghosts, which can do damage but can't heal each other. One ai moved medics with ghosts such that the medics could actually heal. The other ai just left the medics a mile away from the combat, and got slaughtered. Furthermore, the AIs didn't bother with formations, which meant that half their units spent the entire fight trying to get into range. A precombat formation lets almost all the combat units start firing as soon as the fight begins.

3) The red zealots retreated in the face of numerically superior opponents, while the teal zealots just attack moved no matter how many they had. Teal zealots didn't focus fire, which meant that they lose units sooner, and thus had less damage output compared to red. In addition, red failed to kill the pylons (600hp) powering the buildings (a lot more than 600hp). Neither player built their bases to maximize the number of pylons powering their vital gateways; each pylon usually powered only one building.

4) In the fight with dragoons (orange spider things) versus tanks, the protoss (orange) could have frozen half the enemy tanks with a single stasis spell by sneaking the arbiter (flying spider thing) to the back of the tank formation. Furthermore, the protoss could have focused the science vessel (floating teal circle) that was preventing them from being invisible. It would have been a slaughter if the vessel had been focused, as teal would have had no real way to hit the orange units.

5) In the match between Overmind and Krasi0, the article talks about mutalisk clumping preventing some of the mutalisks from attacking. However, the point of the stack is that when one guy is in range, everyone else is. Also, the attack animation is so fast that for all practical purposes, the flyers can shoot while moving. They use their mobility to get out of range of infantry units, then zoom in to pick off outliers when their attack cooldown is finisihed. In actual competition, the terran player would usually rely on a strategic placement of static defenses and a highly mobile cluster. However, the terran (defending force) built tanks, vultures, and goliaths (mech guys that shot missiles) with the flaw that tanks and vultures can't shoot air, and are thus almost useless versus the mutalisks. The mutalisks spent the second half of the clip shooting tanks rather than focusing down the goliaths volleying missiles into them. The terran AI prioritized repairing tanks as much as goliaths, and didn't place tanks next to goliaths to soak up bounce damage from a mutalisk.

In general, the AI had problem with understanding the priority in a fight. That is to say, they often had no sense of what units are critical to a position or what units pose the most threat. They didn't arrange their units to maximize their effectiveness, and often failed to alter their behavior based on the other party. It's a fun contest, but I'm not sure the AIs could beat a moderately skilled player who understands tactics AND strategy.

Re:Several non-obvious flaws (1)

DeadDecoy (877617) | about 4 years ago | (#33911316)

It sounds like the ai is trying to apply an overall strategy where several smaller strategies might make more sense. For instance, you could have ai's for goliaths, infantry, tanks, etc that could be coordinated by a larger, more general strategic ai. The only problem is that most ai's aren't structured as hierarchical models so you lose some of the nuances in using a unit correctly. I bet if you could design a more accurate learning model, it could have something akin to a strategy.

Generic VS Specific (2, Interesting)

Nemyst (1383049) | about 4 years ago | (#33911346)

I think quite a bit of this can be attributed on generic versus specific behavior. I am not an AI programmer, and I just glanced at the page and videos, but from what I gathered most of the AIs had hardcoded strategies that they would follow blindly. Then, the strength of the AI was directly proportional to the quality of the strategy that was implemented. They would use very specific patterns and follow them systematically.

What I would be curious about would be a more generic AI. Instead of using known strategies, the AI would analyze the battlefield and would, for instance, focus fire on support units (not on "medics" or "science vessels", but using the stats of the unit to determine its usage and purpose) or the most dangerous units (air-to-ground would prioritize fire on ground-to-air units) or the most important buildings (using ratios and comparisons to determine this, instead of hardcoding that building A is critical). Technically, it could then be able to react to a lot more situations and would also be adaptable if the fight changes or if the enemy bot has a counter for whatever strategy had been planned. Obviously, a generic bot is harder to build and it might also not be as efficient when compared to singular strategies, but it would be an interesting experiment to make.

knackers (0)

Anonymous Coward | about 4 years ago | (#33911000)

monkey spunk

haha (1)

stoned_hamster (1531291) | about 4 years ago | (#33911958)

jizzed in my pants when I read this finally I get to test the best of the best! and I met a AI sometime last month that *was* more flexible in that it could be any race. It was a little underdeveloped, because it was mostly just a structure for others to add their ideas/AI on. and writing mutating code is VERY hard, especially for SC. give them a break.... please.
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?