Starcraft AI blog

I’ve been watching the replays of Steamhammer’s losses in AIIDE 2017 against its lowest-scoring opponents. I reason that if A beats B nearly every time, then a weakness which causes A to lose to B must be a severe weakness that I should fix.

Steamhammer scored 105-5 against Overkill in this tournament. The losses were all due to the same basic strategy blunder, teching too fast and not making enough mutalisks. One loss was an interesting one that taught me something: It involved making too many devourers.

Here’s the game. Steamhammer played its turtle opening, which it was set to do 1% of the time in ZvZ. (It’s a weak opening, but it is played rarely and it poses challenges that some bots can’t meet, so I don’t mind.) Meanwhile, Overkill also turtled, on 2 bases instead of 1 but with fewer drones.

As in the other losses, Steamhammer spent on zerglings and on teching to hive when it should have been making mutalisks. Overkill flew over, killed a lot of drones—then left for no apparent reason. Overkill was ahead, but Steamhammer could recover. Mistakes like that may explain how Overkill scored so poorly. Steamhammer still didn’t feel like making many mutas, but it did add scourge and morphed a greater spire, which (since it was behind and had already invested in a hive) was reasonable.

Steamhammer started morphing its mutas into devourers. It can’t catch up in mutalisks, so it was a good try to turn the game around. But as I watched, I realized there was a flaw in the strategy logic: It wanted to morph all the mutalisks and go straight devourer. The unit mix is declared as mutalisk + devourer, but because of how gas accounting works, the strategy boss preferred to turn gas-heavy mutas into mineral-heavy devourers.

Overkill finally moved out when it was maxed, with 72 mutalisks. Steamhammer had 20 devourers and 4 mutalisks, plus a fleet of scourge. Now, devourers are support units. They don’t do much damage; their benefit is that they splash acid spores which reduce the enemy’s attack rate and increase the damage taken, and to get the benefit you need fast-attacking units to deal the damage. Because acid spores only stack up to 9, it is not likely that 20 devourers will ever be useful, and definitely not if you fly them around in a group. I guess that about 6 devourers would have been best, certainly not more than 9.

The battle was hilarious. The devourers fought well enough, apparently not harmed by the known bugs, and instantly stacked their purple goop up to the limit of 9 on every Overkill mutalisk that appeared. Devourers are tough, and Overkill’s mutas had their attacks slowed, so the the devourers took a long time to die. But with only 4 mutalisks to deal damage, even though the damage per shot was 9+9 + 3+9 + 1+9 = 40 (spread over 3 enemies with mutalisk bounce) Overkill’s losses were minor.

The ultralisk cavern you can see in the picture was useless. Steamhammer never made an ultra. It shouldn’t have wanted to.

In the next version I’ve taken measures. Steamhammer tries to make more units, techs more moderately, and limits the number of devourers.

I’ve been thinking about how to get Steamhammer to keep trying the gas steal, so the code doesn’t bitrot again. Writing separate gas steal openings for each race doesn’t sound like much fun, and also doesn’t gain the full advantage. I might do a little of that, though.

I decided to build it into the opponent modeling mechanism. I’m not sure about details, but the basic idea is that, against any opponent that is causing trouble, it will try stealing gas to see whether it works. It will record the gas steals in its game records. Over time, the opponent model could learn many things: 1. Which opponents fail to cope; steal gas and win. 2. What opponent builds it is effective to steal gas against. If you see 2 gates and zealots out already (whether or not you’re playing Wuli) then you have the opportunity but there’s little point. 3. How to follow up a gas steal. The point of stealing gas is to channel your opponent’s play into a direction that you can exploit. Then you have to exploit it!

I would also like the opponent model to handle scout timing, but I’m not sure whether I can get to that for the next version.

Gas steal, by the way, is more or less working in my development version. I still have bugs to fix and testing to do, but it’s basically back again. It took a lot of changes.

I thought these 2 games showed interesting mistakes.

Steamhammer-McRave

This game on Circuit Breaker was kind of disorganized on both sides, but fun. Steamhammer played its usual low econ zergling pressure, and McRave opened with cyber core before second gate, which was slow enough to give the pressure a chance. After a few tries, Steamhammer killed enough probes to make up for its own weak economy, and the game was on.

The fight went back and forth, the sides seeming about equal in economic growth, tech progress, and missteps. It was fun to watch.

Steamhammer: It’s only an overlord. No need to keep it safe. And that? Oh, it’s only another overlord.
McRave: Huh? Why wouldn’t I awkwardly split my army?

Then dark templar came out, and Steamhammer fell over. Zerg did not understand.

Steamhammer: What danger? I don’t see any protoss units that I can’t fight.
McRave: Exactly.

Steamhammer-KillAll

This game was a win but... ugh. Only because KillAll went above and beyond to play worse.

KillAll did its thing and sunkened up for safety. Steamhammer understands in outline how to win these games: Place zerglings in a containing position so the enemy can’t expand or attack, make drones while teching, then win with mutalisks. But (as against ZZZKBot in AIIDE) Steamhammer did not execute well. It placed the zerglings in a position that contained nothing, and in fact left the barn door wide open. Steamhammer even stepped back to let enemies pass, in reflexive fear of the distant sunkens.

Below you can see that Steamhammer is ahead in economy, tech, and army—yet Steamhammer is in trouble because its force is out of position, standing outside an enemy base that it cannot threaten while its own base is under attack. Meanwhile, KillAll decided that its attackers should focus down the lair to the exclusion of all other targets, so that Steamhammer’s drones were able to clear the zerglings with no losses.

I can’t say it’s an undeserved win. The winner made smaller mistakes. Only not small mistakes.

Next: Thoughts on the gas steal.

“Somebody” voted in a bunch of Steamhammer versus PurpleWave games. PurpleWave played different openings. Past versions of PurpleWave dominated Steamhammer with the forge-expand opening, taking advantage of Steamhammer’s mistaken macro decisions and weak scouting and tendency to collapse tactically in a big fight. But this PurpleWave has been losing some; it has new weaknesses. So the games are not the best, but they are still interesting.

Some of the games were proxy 2 gates. There were wins and losses, but I found those games not as interesting.

on La Mancha

This is the Steamhammer-PurpleWave game that Nepeta cast last Sunday, so I won’t go into detail. PurpleWave suffered bugs that caused it to warp buildings near the zerg forces and pull probes for no reason, so it did not develop its usual big advantage. What I find interesting about the game is the turning point, when zerg pulled decisively ahead: It was when protoss attacked the zerg natural and dealt great damage, destroying the drones.

The returning zerg army finally cleared the attack. The protoss army was trapped and could not retreat toward home. It should have “retreated” into the zerg main to try to deal more damage (and to pull the zerg army away from the front), but instead turned fatalistic and gave up without a fight. Meanwhile, zerg had many drones at other bases and quickly restored the losses, while the lost protoss army was not as easy to replace. The value of destroying drones depends not on the number of drones you kill, but on the number that survive somewhere....

on Icarus

This game was also a forge-expand, but the play was quite different. No obvious bugs bit. PurpleWave built 4 cannons, which is plenty for most circumstances... and Steamhammer busted them anyway.

Steamhammer killed probes too. Then I tore my hair out in frustration, because instead of pressing for the win, Steamhammer decided it was more important to simultaneously plant a spire, hatchery, evo chamber, and hydra den, and also grow its economy. Notice in the picture that, although Steamhammer has spent 4 drones on buildings, it is still ahead in workers—and PurpleWave has cautiously pulled probes for defense. The spire, by the way, was left unused until late. With 2 bases, PurpleWave eventually caught up from far behind and the game was on again.

Fortunes turned again, like last time, when PurpleWave overpressed and lost too much army at Steamhammer’s natural. Seconds after this picture, protoss went from ahead in army size to well behind. Zerg quickly replaced drone losses and soon broke into the protoss natural in return.

on Destination

PurpleWave went 2 gate zealots into expansion. Neither bot had much understanding of the situation. Steamhammer massed lings, an all-in play to smash the opponent. In practice it’s successful against most bots, but zerg ends up way behind in economy. Protoss can play defensively for a while and then win easily—that’s how Tyr protoss beats Steamhammer.

The game is not long or exciting. PurpleWave expanded in the face of the zerg swarm and did not have enough zealots. I include it to show how little bots understand strategy. In the picture, Steamhammer has half the workers of protoss. With any insight into the army-economy balance, you have to conclude that it is not a time for protoss to take a risk like expanding or moving out. The zealots again went fatalistic; as soon as they realized that they had lost, they stopped fighting and (unable to retreat far) were caught and died. You can also see that in the picture. Steamhammer has related weaknesses that are different but as severe.

PurpleWave might have had a chance if it retreated to the ramp and canceled the nexus. It was the best option, at least.

I expect that PurpleWave will fix its bugs before long and start winning again.

Next: More games, versus McRave and KillAll.

I wasn’t expecting this: Afreeca in Korea pitted 2 low-ranked players against 3 bots each, then Stork against 4 bots (10 games total). The bots are MJbot (which I don’t know anything about), ZZZKBot, and Tscmoo playing random (in a version with a very strange zerg build). Stork also played against CherryPi.

• TeamLiquid thread
• Korean cast (skip ahead to about 40:00 for the first game)
• English cast (missing the first and last games)

Stork made it look easy. If you’re that good, it is easy. It was a treat to see Stork’s superior decisions and strong micro.

Tomorrow: The promised Steamhammer vs. PurpleWave games.