Well, that's fun. I mean, if it works, it works.
Evenly matched armies looking for a micro-based edge turns basically into a fighting game like Street Fighter, where it's about reading your opponent, baiting them into a mistake, pre-empting them, taking decisive action, crisp reflexes/timing, doing something unexpected or unorthodox to get an advantage at a huge risk, etc.
I'm not sure there would need to be that large a skill difference, relatively speaking - worker micro has a really high skill ceiling, and players start with 12 workers instead of 6 nowadays, so 2 extra is a much smaller difference.
Especially in ZvZ where spine crawlers can be built, it's not an auto loss -- it's a bet that the opponent is playing a little greedy, and a chaotic fight.
That's not a worker rush, that's an early pool where you brought some drones.
If it is a viable strategy and not a real edge case to punish some maximal greedy strategy, the game should probably be patched.
It meant that the AI actually found a working strategy against one of the standard bots, where it had not found any before.
It will probably never work when it starts to play against itself, but we don't know if the AI is already at that point.
..what? Thats an absurd consequence -- sc/2 has a hundred different ways to rush, and they all come with the note: if it works, you win, if it doesn't, you're dead. And everyone accepts it. What's so special about drone rushing that it'd receive such consequences?
I mean hell, there's Has specializing in cannon rushing and goes damned far; but drone rushing? No, thats just too much!
I know they have said they will be limiting the maximum APM of the bot to around 180 for the final bot but they may not have implemented it at the time this was happening.
Edit: another example https://www.youtube.com/watch?v=IKVFZ28ybQs
As far as I can tell, the AI must be cheating, at the very least to obtain map vision beyond what is available in a match. In order for the zerg AI to observe each tank's turret rotation and predict which zergling it's about to fire on, zerglings have a sight radius of 8, smaller than the tank's 11. In a fair match, the zerglings would be fired on before getting a chance to see the tanks. Even as the group of zerglings gets close enough to see the first tanks, other tanks start firing from beyond the zerglings' vision, so I'm not convinced this AI could pull this off in an actual match.
If it's playing against the Starcraft 2 blizzard AI, it will learn a lot of "bad habits" because outright bad strategies work against the AI. Thus the worker rushing.
The reason is that while the attacking player sends over their workers to attack, the defending player is still constantly making workers. By the time that attackers get there the defending player should have more workers. He simply has to command all of them to fight the opponent's workers.
If the opponent doesn't react, you win because you kill all their workers.
If the opponent overreacts, you win because you are mining more than them (IIRC this is a problem with the insane ai).
If the opponent reacts poorly in other ways, you might be able to win by out microing them. E.g. SCVs (terran workers) consistently beat drones/probe (the other races workers) 1-1 without micro. Repairing can be an advantage. The offensive AI being better at stacking damage on a few units. Etc.
The defensive AI should learn to fix these problems and stop losing to worker rushes, but it could take awhile. In other words the defensive AI starts out as a lower ranked player.
PS. I'm not sure how serious a tournament this was, but here's an example of a real worker rush (not an early pool with workers attached): https://www.youtube.com/watch?v=_AtqgaJzJP4
Of course you lose all of that time it takes for your workers to drive across the map, so it's a pretty dicey strategy. A 50% win rate against the AI sounds about right.
Your "reasoning" is actually a false perception. It doesn't make these mistakes and tries strategies that seem improbable to human players.
A 50% win rate against the Insane AI is very good, as at the higher AI levels the computer actually cheats (no fog of war, more resources, etc).
The AI cheats, but is also incredibly predictible, and bad at decision-making.
If you do this long enough you can build a virtually undefeatable siege tank army that the AI would simply smash its face into, and then corral them to 2 or 3 bases. They would always run out of minerals while I expanded everywhere and slowly inched tanks forward. Doing this same strategy against humans got me to about gold tier in the early days of sc2.
Using this strategy is objectively bad in that it can be repelled by an opponent almost regardless of their initial strategy.
If deepmind’s goal is to beat the standard Ai, then sure I guess it understands that. But that’s a very different problem from understanding Starcraft, and a much less difficult one at that.
And once the defense gets good enough, the attack portion of the AI should probably do the worker rushes much less often.
Of course, given that the AI has different constraints in micro-management and attention, and that the game is balanced given human skills, some things that would be totally bonkers to do as a human might work for the AI.
Or is "understanding" an attribute which is only afforded to humans who do these things, much like a machine can process the same inputs in the same ways as a human but will probably never be considered to have 'qualia'?
> After feeding the agent replays from real players, it started to execute standard macro-focused strategies, as well as defend against aggressive tactics such as cannon rushes.
It's not my fault if you don't scout. Planetary Fortress rushes, proxy barracks, cannon rush... it's all fair game.
> Scholar's Mate has sometimes also been given other names in English, such as Schoolboy's Mate (which in modern English perhaps better connotes the sense of 'novice' intended by the word Scholar's) and Blitzkrieg (German for "lightning war"), meaning a quick and short engagement (Kidder 1960).
The problem is that there's a sort of rock-paper-scissors game of (conservative)-(greedy)-(all in). That is, a player who build defenses early on will crush a worker rush but they'll be far behind a player who ignores defenses and focuses on growing their economy. The worker rush is designed to punish this greedy build order.
There's nothing that can be done, really. If you decide to send a worker to scout super early on then your economy suffers so much that you'll be behind no matter what you do.
Edit: to those of you drawing a distinction between an immediate worker rush and something like an early pool or a cannon rush, that's splitting hairs. These are all classified as all-in strategies that almost automatically lose if they encounter a conservative build order.
Things like early pools and cannon rushes are (depending on the details of the meta at the time) a rock papers scissors game. Cheese (early pool/cannon rush) beats aggressive play beats conservative play beats cheese (roughly speaking).
Worker rushes are just bad. Apart from playing against 6 pools on really old versions of SC2 on maps with ridiculously short rush distances they just lose. Even then I don't think I'd call them good.
The term means you take your initial workers and charge the enemy. If you know where the enemy is you'll arrive about the time they are up one or two workers on you, then you just have to fight when you're down one or two workers and you can't back off (they'll return to mine).
A human can win like this if they are so much better at micro that they can overcome the material disadvantage (unlikely) or if their opponent panicks and does something dumb (e.g. pulling only half their workers to fight).
Because worker rushes arrive so early it doesn't matter what plan you have for the match, you'll have at least as many workers (if you are also worker rushing) or you'll have more. Maybe if you're going six pool you'll have fewer but you'll also be able to get lings and win with them.
The computer can lose to worker rushing only because it can get caught in loops of poor decisions (e.g. you lure away a couple workers and kill them).
Worker rushing is always a bad plan.
As the grandparent stated, a worker rush only works against the built in starcraft computer player, because the computer AI is too dumb to recognize "I am being worker rushed" and may not commit all of its workers to defending.
This is common technique, mostly used to get scouting drone back through a walloff (own unit stands on "hold" in a small choke) or when a mineral line is under siege (e.g. Siege Tank, Liberator), the player can select all his workers to mine a single mineral patch (has to be spammed, otherwise workers redistribute) outside of the siege range until they siege is cleared up.
That might solve its task, but it’s a far cry from learning to play Starcraft well. I was surprised they seemed to have trained it against the standard Ai as that’s not useful.