Using genetic algorithms to find Starcraft 2 build orders
1–10 of 79 posts
Re: Using genetic algorithms to find Starcraft 2 build orders
#2This echoes the story of Eurisko, a genetic AI written by Stanford's Douglas Lenat to build Traveller "Trillion Credit Fleets." Eurisko destroyed the competition at the national championship 2 years in row.
http://aliciapatterson.org/APF0704/Johnson/Johnson.html
In both cases, using the GA allowed a player to more comprehensively search the opportunity space created by the game designers than the designers did during design and play testing.
Really awesome stuff, though it sets up an intriguing arm's race between the game designers who can patch and Nerf elements to eliminate unbalanced strategies and the players who then explore the new rule set.
Re: Using genetic algorithms to find Starcraft 2 build orders
#3This echoes the story of Eurisko, a genetic AI written by Stanford's Douglas Lenat to build Traveller "Trillion Credit Fleets." Eurisko destroyed the competition at the national championship 2 years in row. http://aliciapatterson.org/APF0704/Johnson/Johnson.html In both cases, using the GA allowed a player to more comprehensively search the opportunity space created by the game designers than the designers did during…
It's sad that they banned him. What kind of logic is this? Do they really think it would stop other players from doing the same?
Re: Using genetic algorithms to find Starcraft 2 build orders
#4This is pretty cool to see programs "solving" video games. Although, for the most part I don't think this will affect play much. All-in strategies like this tend to only work if the other player is unprepared. Granted, this is a very fast rush and perhaps still very difficult to scout and notice early enough to counter, but the Starcraft community does tend to go back and forth finding and countering new builds (Perhaps the next step is to use a program to find a counter to this).
The two points about the build that the article mentions as counter-intuitive don't seem that strange to me since it is a rush (all-in) build. The extractor trick is well known and I would believe that it sacrifices economy long term but it gives you an extra drone (= more money) early on which is good for a rush.
The double overlord is there to support the seven roaches that you build almost all at once. At the beginning of the game, you can only afford to build one unit at a time so you can also replenish supply one overlord at a time. As the game progresses and you start pumping out large number of units at a time, you have to also be producing multiple overlords simultaneously to keep up with supply. Although this is very early, the all-in rush to produce 7 roaches requires a fast increase in supply.
To give an idea of how fast this is, the build ends at around 31 supply, about half of which is the attacking roach units. Max supply is 200 and mid-game is probably somewhere around 50-70 supply.
Re: Using genetic algorithms to find Starcraft 2 build orders
#5This is pretty cool to see programs "solving" video games. Although, for the most part I don't think this will affect play much. All-in strategies like this tend to only work if the other player is unprepared. Granted, this is a very fast rush and perhaps still very difficult to scout and notice early enough to counter, but the Starcraft community does tend to go back and forth finding and countering new builds (Perh…
I haven't looked into SC2 as much, but in the BW version of the the extractor trick, the cost-benefit tips at some point within the timespan of 'rushes'. That is, it'll be wonderful for very very fast rushes, but more 'patient' rushes are harmed by it. And at least for BW rushes, the trend seemed to be in the last bit before SC2 came out to trend towards more patient rushes. People weren't even looking for the win off the rushes anymore, but rather some sort of fast econ harrass to early map control. That mind set, where fast extractor tricks were optimal probably carried over a bit into the SC2 build making process.
Re: Using genetic algorithms to find Starcraft 2 build orders
#6This is pretty cool to see programs "solving" video games. Although, for the most part I don't think this will affect play much. All-in strategies like this tend to only work if the other player is unprepared. Granted, this is a very fast rush and perhaps still very difficult to scout and notice early enough to counter, but the Starcraft community does tend to go back and forth finding and countering new builds (Perh…
I haven't looked into SC2 as much, but in the BW version of the the extractor trick, the cost-benefit tips at some point within the timespan of 'rushes'. That is, it'll be wonderful for very very fast rushes, but more 'patient' rushes are harmed by it. And at least for BW rushes, the trend seemed to be in the last bit before SC2 came out to trend towards more patient rushes. People weren't even looking for the win of…
Yes, most high level play isn't really looking to do all-in rushes like this. The goal is more to "fast econ harrass to early map control" giving you an early advantage and allowing you to eventually win.
Re: Using genetic algorithms to find Starcraft 2 build orders
#7Earlier quoted context omitted.
I haven't looked into SC2 as much, but in the BW version of the the extractor trick, the cost-benefit tips at some point within the timespan of 'rushes'. That is, it'll be wonderful for very very fast rushes, but more 'patient' rushes are harmed by it. And at least for BW rushes, the trend seemed to be in the last bit before SC2 came out to trend towards more patient rushes. People weren't even looking for the win of…
Yes, most high level play isn't really looking to do all-in rushes like this. The goal is more to "fast econ harrass to early map control" giving you an early advantage and allowing you to eventually win.
I'd have to disagree regarding rushes in high level play. I most enjoy 4v4 random and a key move is decimating one opponent's economy to the point that they become a non-factor in the game. With this build order in a 4v4 one player can neutralize a Protoss or Zerg player and then pivot to mutas or continue with roach/hydra. Since your economy isn't in shambles like a traditional 6 pool zergling rush, even if you fail with the roaches you are still left in acceptable shape to assist your teammates.
I specify this being useful in 4v4 against Protoss/Zerg as Terran traditionally wall and the few seconds it takes to burst through the wall may give their teammates time to mobilize.
Note- I wrote this under the impression that your mentioning "all-in rushes" didn't include sending your drones in to act as meat shields. In a 4v4 that would be suicide and invalidate my point.
Re: Using genetic algorithms to find Starcraft 2 build orders
#8This echoes the story of Eurisko, a genetic AI written by Stanford's Douglas Lenat to build Traveller "Trillion Credit Fleets." Eurisko destroyed the competition at the national championship 2 years in row. http://aliciapatterson.org/APF0704/Johnson/Johnson.html In both cases, using the GA allowed a player to more comprehensively search the opportunity space created by the game designers than the designers did during…
It's sad that they banned him. What kind of logic is this? Do they really think it would stop other players from doing the same?
IIRC they didn't ban him - rather, they told him that if he kept competing they'd just cancel the competition. This was not out of spite, but because he was so dominant that it was discouraging the other players from even trying.
Re: Using genetic algorithms to find Starcraft 2 build orders
#9Starcraft has always struck me as a game of compound interest, and the optimal early builds always seem to be just that: maximizing an instantaneous rate-of-production, which will correlate to maximizing your instantaneous rates-of-doing-damage
It's always seemed like more of an economic strategy game than an actual "fronts of battle" kind of strategy.
Re: Using genetic algorithms to find Starcraft 2 build orders
#10Starcraft has always struck me as a game of compound interest, and the optimal early builds always seem to be just that: maximizing an instantaneous rate-of-production, which will correlate to maximizing your instantaneous rates-of-doing-damage It's always seemed like more of an economic strategy game than an actual "fronts of battle" kind of strategy.
That's true, but if you're evenly matched with your opponent, your initial economic curves will be identical, and then strategy and tactics come into play. Obviously it can be more valuable to strike the opponent's miners and factories than to engage his main army -- but real war is no different.