Steamhammer defeated IceBot 2-0 in SSCAIT 2016, but the numbers are deceiving. In the first game, IceBot built its strongpoint defense with a bunker surrounded by turrets, Steamhammer became obsessed with the bunker but was barely able to attack it, and IceBot countered the mutalisks in good time with goliaths and valkyries. Steamhammer was falling behind, but took more bases. IceBot moved out with an unstoppable army and crushed the zerg natural and main; Steamhammer was still able to stop dropship harassment with its remaining army, but zerg was dead. Then IceBot crashed.
The only good news is that I taught Steamhammer 0.2 that dropships are critical targets and must be eliminated. IceBot’s drop attempts were shut down hard and only hurt terran. In every other way, IceBot played better.
The second game was exciting. IceBot again built its strongpoint defense and Steamhammer again became obsessed with the bunker. But for some reason IceBot did not raise the mutalisk defense flag, and instead kept pushing columns of marines out beyond turret range to die. Steamhammer took more bases, its mutalisk flock was growing, and it was upgrading air carapace. It even made some dents in the strongpoint, destroying the first bunker. IceBot also took two side bases, and Steamhammer did not scout them, much less attack. IceBot finally switched to goliaths and valkyries, but by then the mutalisks were so strong that they could fight on even terms. IceBot made its big tank push, but the push was defeated. Steamhammer had most of the map and IceBot could not expand any more, but terran tried to stay in the game with drops and vulture harassment and long distance mining. In the end IceBot mined out and Steamhammer was still going, the terran army wore away to nothing, and the strongpoint finally fell like the gate to a fortress. Good game.
Steamhammer showed a lot of weaknesses, but the key one was the obsession with that bunker. It turns out that there are multiple causes. One cause is that bunkers were given high priority as targets, so that mutalisks would attack an empty bunker surrounded by turrets and ignore the turrets and other enemies. I made a quick fix for that in the next version. Another cause has to do with the way squad orders are computed. It turns out that squad orders made based on early scouting tend to direct play for the rest of the game. I’m still thinking about that one; my first attempt to fix it is no good. A third cause is the way it calculates whether a bunker can be successfully attacked. SparCraft does not support bunkers, but bunkers can’t be ignored. Dave Churchill’s workaround was to pretend that a bunker is actually 5 marines with hitpoints pro-rated based on the bunker’s health! It’s an ingenious idea, but it’s also a poor approximation. The damage rate is wrong, the health is wrong, and the 5 imaginary marines can be shot down one by one. SparCraft will need some work.
At some point I’ll study SparCraft closely and improve it. It seems reasonably accurate, but it’s not all the way there. On the one hand, SparCraft doesn’t support every unit. On the other, SparCraft does seem to support medic healing and unit upgrades, but UAlbertaBot does not take advantage of the support. Well, one step at a time. It’s not a priority yet.
