Starcraft AI blog

In 2020, I analyzed McRave’s three-part strategy representation. This version of McRave is the CoG 2022 version, and I think details have changed, but the basic structure is the same as in 2020.

With its deadly mutalisks, McRave apparently does not bother to learn what to play against zerg opponents. In ZvZ, it follows the same 9 pool into one hatch muta strategy every game. It went mutas in most games against terran and protoss, too. But it’s still interesting to see what it recognized in its opponents play.

Microwave is configured to save only the most recent 200 game records. There were 290 rounds, so where all games were played, it dropped data for 90 games. (Steamhammer is configured the same way, though the data it stores is quite different.)

Mutalisks were good—relatively speaking—even though this version of BananaBrain goes heavy on the corsairs. Even the slow-starting 3 hatch muta was more successful than most builds. It’s curious that the highest win rate came when Microwave was unable to figure out what opening BananaBrain was playing. I doubt the cost of scouting is that high. I’m guessing it’s more likely that scouting failed more often when starting positions were distant. That gave Microwave more time to prepare.

But Stardust was (a little) vulnerable to zerglings. Again, the highest win rate came when Microwave did not know what Stardust was doing.

PurpleWave just fell over to Microwave’s zerglings. But even here, an Unknown enemy build was good news for Microwave.

Steamhammer was also successful with zerglings (I’ll post its data when I get to it), but nothing like this successful. I expect that, true to its name, Microwave has superior zergling micro. Though maybe it’s just more aggressive?

A lot of openings are roughly equal. I suspect that some of the ones that scored 0 would have also been roughly equal if they’d been tried more times.

So: Good with zerglings, not so good with mutalisks. Microwave knows how to defend its bases with two spore colonies each, in the standard pro way, but apparently that’s not enough to survive against McRave.

The two top builds are 5 hatcheries before spawning pool. Compare Dragon’s table for Microwave, which says that opening with mass vultures was best. The vultures must have often come before Microwave could defend itself.

Once the opening build is over, Dragon adapts to the opponent’s unit mix and many of its games start to look similar. Nevertheless, the opening makes a big difference in how the game comes out.

The “dirty worker rush” is a late rush with a lot of SCVs. You have to be ready for it, but if you are, it’s easy to beat.

opening	total	#1 bananab	#2 stardus	#3 purplew	#4 steamha	#5 mcrave	#6 microwa	#7 dragon	#9 infeste
total	-  31%	5-279  2%	25-263  9%	53-236  18%	9-274  3%	183-102  64%	112-170  40%	48-236  17%	263-26  91%
4RaxMarines	8-117 6%	0-19 0%	5-33 13%	0-11 0%	0-22 0%	-	3-16 16%	0-16 0%	-
MarineRush	181-240 43%	2-25 7%	1-18 5%	14-54 21%	1-28 3%	65-30 68%	18-45 29%	3-29 9%	77-11 88%
TankPush	1-89 1%	0-18 0%	1-16 6%	0-11 0%	0-21 0%	-	0-7 0%	0-16 0%	-
VultureRush	1-90 1%	0-18 0%	0-12 0%	0-11 0%	0-21 0%	-	0-7 0%	1-21 5%	-
DTRush	24-177 12%	1-40 2%	0-25 0%	3-41 7%	0-18 0%	-	-	20-53 27%	-
DragoonRush	2-119 2%	0-32 0%	2-39 5%	0-22 0%	0-18 0%	-	-	0-8 0%	-
ZealotRush	229-236 49%	0-32 0%	2-39 5%	0-22 0%	8-54 13%	62-46 57%	59-23 72%	3-18 14%	95-2 98%
2HatchHydra	44-143 24%	1-27 4%	0-10 0%	32-44 42%	0-23 0%	-	2-10 17%	9-29 24%	-
3HatchMuta	1-73 1%	0-21 0%	0-10 0%	0-4 0%	0-23 0%	-	0-5 0%	1-10 9%	-
3HatchScourge	1-73 1%	0-20 0%	1-14 7%	0-4 0%	0-23 0%	-	0-5 0%	0-7 0%	-
ZerglingRush	206-229 47%	1-27 4%	13-47 22%	4-12 25%	0-23 0%	56-26 68%	30-52 37%	11-29 28%	91-13 88%

UAlbertaBot’s primary builds are MarineRush, ZealotRush (9-9 gates), and ZerglingRush (5 pool). Against #5 McRave and #9 InfestedArtosis, it stuck with them. Against other opponents it experimented with alternatives to try to escape its losses. It found 4RaxMarines (barracks at 4 supply) against #2 Stardust, 2HatchHydra against #3 PurpleWave, and DTRush against #7 Dragon.

I uploaded Steamhammer 3.6 to SSCAIT. It turns out that Steamhammer terran needs a bug fix, so no Randomhammer for now. It will have to wait for my traditional post-AIIDE bugfix version.

As I mentioned earlier, I’ll post the change list after I’ve fixed up the blog. First things first.

Steamhammer is submitted for AIIDE 2023. You bring the futile hopes, I’ll bring the lurker spines.

It was kind of a scramble this year, though. Yesterday when I did what was supposed to be the final round of major tests, I turned up 3 critical bugs, 2 in new features and 1 left over from who knows when, hidden from view because the opponent model learned to avoid playing into it. As I stayed up late last night frantically debugging, a cricket got into the house—into the same room—and started talking loudly with its friends outside. Not entirely relaxing! But I got up early in the morning and finished fixing everything, and ran more tests, and packed it up, and ran the did-I-pack-it-up-correctly checks and tests, and now it’s on its way.

Last year, Steamhammer scored about 8% against BananaBrain, which finished first. BananaBrain has improved since then, but I expect to score substantially higher against it this year. Well, I could have missed further bugs, but there was no sign of it in what I had time for. My very last test game was against BananaBrain. It was hard-fought and went to late game, and zerg lost narrowly. Steamhammer managed to parasite every shuttle, and plague a lot of armies.

Next: Fixing the blog comments is my first priority. Then I’ll release Steamhammer and write up its changes.

As you might guess from the CoG results, Stardust has gained strong new skills since last year. Against zerg in particular, one skill is that it uses corsairs heavily. Another is that it learned the forge expand opening. And yet it can still be defeated.

CherryPi is from 2017, but it shows how. The SSCAIT game Stardust v CherryPi is instructive (I kept the replay for when SSCAIT recycles it).

The recipe is:

1. Facing forge expand, play a greedy opening. CherryPi opened pool first (with a rare 13 pool) so that it could make zerglings if it needed to, but cannons were not going to walk across the map to attack, so it followed up with drones and hatcheries.

2. Fight efficiently in the middle game. CherryPi could not take any one-sided victories against such a tough opponent, but it traded well and cut the protoss army down to a safe size, where zerg could spawn enough defensive units in the time the protoss would take to cross the map.

3. With that breathing room, zerg could safely pull ahead in workers. Then it was just mass and smash.

See how easy it is? It’s a simple matter of being good at everything!

Of course it was only possible because Stardust showed weaknesses. One is that it was cautious and clumsy with its corsairs, and put on less counter-air pressure than it could have. First it kept them with the army, then it flew them over hydras.

Three items.

1. Steamhammer is coming along nicely. Today I completed and tested new infrastructure that will make it easy to solve one of Steamhammer’s biggest weaknesses, and bring other play improvements closer too. There’s not much time before the AIIDE submission deadline, but even so, expect harder fights.

2. Blog comments turn out to not be the only problem with the blog. I need to do some sysadmin stuff that I find tedious, and I don’t want to be distracted from working on Steamhammer. I’ll get around to it sometime in September for sure. Sorry. :-( I miss the good comments.

3. CoG has not posted results on its website, not even summary results. If and when they appear, I’ll do at least some of my usual analysis.

To fill the dead air while I try to fix the absurdly undiagnosable comment bug, here’s a game I was pleased with.

Steamhammer - BananaBrain on Python was played not long ago. (Here’s the replay.) BananaBrain held the initiative for most of the game, and broke into the zerg natural at one point, but never destroyed a completed zerg base. The game has plague, parasite, and broodling.

Steamhammer’s favorite strategy is to overrun you in the late game. Even strong opponents lose if they let the strategy play out.

AIIDE. Steamhammer will play in AIIDE again this year. I expect to bring a new version—it has been too long. Steamhammer’s infrastructure for some important new skills is almost ready, so if all goes as it should I will shatter your futile hopes with lurker spines!

I like the map rules this year: Five chosen from last year’s maps, five from a long list of varied maps. It’s a compromise between the guaranteed quality of a fixed map pool and CoG’s historical plan of selecting the maps from a list with inconsistent quality, some of which bots struggle on. The AIIDE list is large but sorted by quality, and the allowed maps have relatively few features that bots can’t cope with. Well, the list is long enough that there are several maps I don’t recognize.

I have often tested Steamhammer on random maps from a large collection, including utterly nonstandard Blizzard maps. It’s not good (yet) at taking advantage of map features, but it’s solid and consistent on standard-ish maps. It may be to my advantage.

CoG. The conference runs from 21-24 August, so results should be out soon. The roster includes one new bot, ProtossPleb, whose name and information does not look promising in itself. But we’ll see. The other participants are several familiar top finishers.

ASL Season 16 started this week. No great games so far, but I enjoyed Calm’s clever play against Rain in group B of the round of 24. The best games are often in the round of 8.

I tried turning comments back on, but it seems the feature grew a technical problem on the new webhost. Stand by for repairs.

I re-enabled Randomhammer on SSCAIT. It was disabled for the tournament. There are no updates to the code.

I disabled it on 19 December by uploading an empty zip. Strangely, Randomhammer’s game history shows 5 games played between 30 January and 4 February (today). Since there was no bot to run, the Randomhammer player did not do anything.

Steamhammer won all but 2 of its regames, shifting its score up minutely from 79-33 to 80-32. It is tied with WillyT, which means it’s not definite which opponent it will face. Depending on whatever rule is used to pair tied bots, it might face Hao Pan, PurpleWave, or Dragon. PurpleWave is a possible opponent only if Hao Pan wins its last regame, which is likely.

Halo by Hao Pan would be its ideal opponent. Steamhammer would stand a good chance to upset the higher ranked bot.

PurpleWave would almost certainly win.

Dragon is in between. Steamhammer’s score ratio versus Dragon on BASIL is around 2:3, so it has a theoretical chance of winning a match. But Steamhammer will do worse on SSCAIT because it has less data to go on. There would be a slight chance of an upset.

I may not have updated Steamhammer in 2022, but I am still following SSCAIT. I’m watching a lot of the games, and especially all Steamhammer games.

Krasi0 is participating, after sitting out recent tournaments. It has been missed.

I expect the top to be fought between Krasi0, Stardust, and BananaBrain. Krasi0 is the favorite to win the round robin phase. Monster has slipped a little as a few opponents have learned how to deal with it. PurpleWave put on a clinic for how to beat Monster as protoss, and so did Krasi0 as terran. Both won with one-base timing attacks at an early point when Monster’s build was weak. Monster needed better understanding of the opponent’s build to adapt. (Monster’s ZvZ build and adaptation are different, so zerg can’t simply copy the timing.)

PurpleWave is following its pattern of excellent preparation against key opponents it will face in the elimination phase, along with stray losses to weaker opponents. Will it be good enough to win the elimination phase and be the overall winner?

So far Steamhammer has been holding a position at the bottom of the top 16, with only slight wobbles. But the tournament is young. I expect it to finish about the same as last year. Only its top opponents have improved much, and they are all ranked higher anyway! And Steamhammer’s learning tends to make it robust against moderate updates to its opponents, at least once it has had time to adjust. But then, I have been over-optimistic in the past.

Microwave’s history files are completely different from Steamhammer’s, but it’s hard to tell the difference from this summary. The opening names and recognized strategies look alike. They even both recorded 200 games of the 220 or so that were played per opponent.

They’re different in that I can’t speak to Microwave’s exploration strategy.

Steamhammer did not record all games, only the last 200. I’ll mention my preparation for different opponents, because it makes a big difference.

Steamhammer’s gas steal achieved nothing significant against any opponent. Maybe next year I’ll disable it.