archive by month
Skip to content

AIIDE 2021 - what McRave learned

I’m taking the bots in finishing order; McRave is next. Last year I analyzed McRave’s three-part strategy representation and learning algorithm. These apparently have not changed in outline, though details may have changed. The set of available strategies has been updated. For example, 6HatchHydra is new this year. It follows that the set of enabled strategy triples has also changed.

McRave is much stronger this year. It has become noted for dangerous mutalisk control.


#1 stardust

openinggameswinsfirstlast
HatchPool,12Hatch,2HatchMuta816%0156
PoolHatch,9Pool,2HatchMuta2214%13155
PoolHatch,9Pool,3HatchMuta110%4147
PoolHatch,9Pool,6HatchHydra90%9143
PoolHatch,Overpool,2HatchMuta90%6145
PoolHatch,Overpool,3HatchMuta138%11125
PoolHatch,Overpool,6HatchHydra120%1149
7 openings1576%
enemygameswins
1GateCore,2Zealot,4Gate1056%
2Gate,10/12,4Gate1010%
2Gate,10/17,4Gate405%
2Gate,9/9,4Gate10%
2Gate,Unknown,4Gate10%
5 openings1576%


9 pool into 2 hatch muta worked best, with 3 wins out of 22. That is not intuitive. The more natural 12 hatch into 2 hatch muta was tried more but was less successful. Did Stardust react inefficiently to the 9 pool? McRave appears to correctly understand that Stardust ends up with 4 gates despite taking different routes to get there. That’s kind of impressive.

Last year McRave scored 3 out of 150 against Stardust. This year it scored 8 out of 150 against a stronger Stardust—which seems to have updates specifically to defeat McRave, since McRave was the only bot to upset it in CoG 2021. Good progress!


#2 bananabrain

openinggameswinsfirstlast
HatchPool,12Hatch,2HatchMuta8619%0156
HatchPool,12Hatch,2HatchSpeedling10%2626
HatchPool,9Pool,2HatchSpeedling2100%30100
PoolHatch,9Pool,2HatchMuta1520%18144
PoolHatch,9Pool,2HatchSpeedling30%2429
PoolHatch,9Pool,3HatchMuta1921%4124
PoolHatch,9Pool,6HatchHydra20%12129
PoolHatch,Overpool,2HatchMuta40%996
PoolHatch,Overpool,2HatchSpeedling10%2525
PoolHatch,Overpool,3HatchMuta1421%16114
PoolHatch,Overpool,6HatchHydra100%1146
11 openings15718%
enemygameswins
1GateCore,2Zealot,Corsair3113%
1GateCore,2Zealot,DT812%
1GateCore,Unknown,Corsair1010%
1GateCore,Unknown,DT60%
2Gate,10/12,4Gate10%
2Gate,10/12,Corsair3116%
2Gate,10/12,DT1127%
2Gate,10/12,ZealotRush70%
2Gate,10/17,4Gate367%
2Gate,10/17,Corsair30%
2Gate,10/17,DT250%
2Gate,9/9,Corsair333%
2Gate,9/9,DT20%
2Gate,9/9,Unknown10%
2Gate,Proxy,ZealotRush729%
2Gate,Unknown,Corsair20%
FFE,Forge,5GateGoon922%
FFE,Forge,Speedlot729%
FFE,Forge,Unknown520%
FFE,Gateway,5GateGoon1100%
FFE,Gateway,Unknown10%
FFE,Nexus,5GateGoon425%
FFE,Nexus,Speedlot10%
FFE,Nexus,Unknown1100%
24 openings15718%


McRave’s wins over BananaBrain are dominated by games where BananaBrain timed out. In game 2754, BananaBrained timed out with 320 frames over 55ms, when McRave had 318 frames over 55ms—close call! McRave had more timeouts than any other bot, but only 3 losses to BananaBrain by timeout. BananaBrain’s timeouts seem to be concentrated on Dragon and McRave, and to a lesser extent on Steamhammer.

If HatchPool,9Pool,2HatchSpeedling was tried twice and won twice, why wasn’t it tried more often? The first try was on game 30 of 0-156. I imagine that it was a reactive build, not enabled as an initial choice but switched to under given circumstances. I didn’t read the source to verify that.

The enemy table shows a complex set of strategies by BananaBrain.


#3 dragon

openinggameswinsfirstlast
HatchPool,12Hatch,2HatchMuta6632%0156
HatchPool,12Hatch,2HatchSpeedling10%6161
PoolHatch,12Pool,2HatchMuta911%27150
PoolHatch,12Pool,3HatchMuta3741%1129
PoolHatch,Overpool,2HatchMuta2733%3127
PoolHatch,Overpool,2HatchSpeedling2100%2199
PoolHatch,Overpool,3HatchMuta1527%25148
7 openings15733%
enemygameswins
2Rax,Expand,Unknown1100%
2Rax,Main,1FactTanks10%
2Rax,Main,Unknown825%
2Rax,Proxy,Unknown10%
RaxCC,1RaxFE,1FactTanks333%
RaxCC,1RaxFE,5FactGoliath2512%
RaxCC,1RaxFE,Unknown1127%
RaxFact,Unknown,2PortWraith1100%
RaxFact,Unknown,5FactGoliath1323%
RaxFact,Unknown,Unknown250%
Unknown,Unknown,Unknown8939%
Unknown,Unknown,WorkerRush2100%
12 openings15733%


Over half of McRave’s losses to Dragon were by timeout. I think Dragon is an especially easy bot to time out against, because its strong macro and big battles with light units put heavy demands on the opponent.

The enemy table shows 89 games with Unknown,Unknown,Unknown. Apparently Dragon often denied scouting. Presumably the scouting overlord was afraid to approach due to marines, and any scouting drone was turned away. Also, I wonder about 2Rax,Proxy,Unknown. Did Dragon really proxy once, or was it a misrecognition? On Python, bases can be close by air. If McRave measures proxy distance by air distance, it might take a barracks in the enemy main for a proxy.


#4 steamhammer

openinggameswinsfirstlast
PoolHatch,12Pool,2HatchMuta2133%3142
PoolHatch,12Pool,2HatchSpeedling1217%1136
PoolLair,9Pool,1HatchMuta12551%0157
3 openings15846%
enemygameswins
HatchPool,10Hatch,1HatchMuta2100%
HatchPool,10Hatch,2HatchSpeedling1681%
HatchPool,10Hatch,3HatchMuta10%
HatchPool,10Hatch,Unknown850%
HatchPool,9Pool,3HatchMuta10%
HatchPool,9Pool,Unknown667%
HatchPool,Unknown,Unknown1100%
PoolHatch,12Pool,3HatchMuta1100%
PoolHatch,12Pool,Unknown250%
PoolHatch,4Pool,LingRush888%
PoolHatch,9Pool,2HatchSpeedling1100%
PoolHatch,9Pool,Unknown838%
PoolHatch,Unknown,2HatchHydra1100%
PoolHatch,Unknown,3HatchMuta2100%
PoolHatch,Unknown,Unknown475%
PoolLair,9Pool,1HatchMuta2100%
PoolLair,Unknown,1HatchMuta425%
Unknown,Unknown,1HatchHydra1100%
Unknown,Unknown,1HatchLurker2100%
Unknown,Unknown,1HatchMuta5127%
Unknown,Unknown,3HatchMuta20%
Unknown,Unknown,Unknown3429%
22 openings15846%


McRave chose from the same fixed set of 3 strategies against all the zergs. Only the 1 hatch mutalisks were able to hold their own with Steamhammer.


#6 willyt

openinggameswinsfirstlast
HatchPool,12Hatch,2HatchMuta8933%0156
PoolHatch,12Pool,3HatchMuta5535%1155
PoolHatch,Overpool,2HatchMuta130%2151
3 openings15731%
enemygameswins
RaxCC,1RaxFE,1FactTanks200%
RaxCC,1RaxFE,5FactGoliath3826%
RaxCC,1RaxFE,Unknown3033%
RaxFact,Unknown,5FactGoliath20%
Unknown,Unknown,Unknown6742%
5 openings15731%


Hurrying the mutas too much did not help against WillyT. The enemy table shows that WillyT sometimes countered with goliaths. Does McRave later make a hydra switch to fight the goliaths? WillyT sometimes goes for goliaths with 2 tanks, and it’s sensible to fight back with hydralisks. I didn’t see a hydra switch in the games I watched.

I noticed that McRave doesn’t clear the terran scout from its main until mutas come out. WillyT gets to know the exact timing for its turrets with no need to spend a scan.


#7 microwave

openinggameswinsfirstlast
PoolHatch,12Pool,2HatchMuta4965%3156
PoolHatch,12Pool,2HatchSpeedling1533%1147
PoolLair,9Pool,1HatchMuta9362%0149
3 openings15761%
enemygameswins
HatchPool,10Hatch,+1Ling10%
HatchPool,10Hatch,1HatchMuta10%
HatchPool,10Hatch,2HatchHydra1100%
HatchPool,10Hatch,2HatchSpeedling4146%
HatchPool,10Hatch,3HatchMuta1182%
HatchPool,10Hatch,Unknown1867%
HatchPool,9Pool,+1Ling10%
HatchPool,9Pool,2HatchSpeedling2100%
HatchPool,9Pool,3HatchMuta250%
HatchPool,9Pool,Unknown2100%
HatchPool,Unknown,2HatchSpeedling250%
PoolHatch,12Pool,+1Ling1100%
PoolHatch,12Pool,1HatchHydra1100%
PoolHatch,12Pool,2HatchSpeedling1100%
PoolHatch,12Pool,3HatchHydra1100%
PoolHatch,12Pool,3HatchMuta922%
PoolHatch,12Pool,Unknown580%
PoolHatch,4Pool,LingRush1479%
PoolHatch,9Pool,+1Ling10%
PoolHatch,9Pool,1HatchMuta10%
PoolHatch,9Pool,2HatchSpeedling1100%
PoolHatch,9Pool,3HatchMuta367%
PoolHatch,9Pool,Unknown250%
PoolHatch,Unknown,2HatchHydra1100%
PoolHatch,Unknown,Unknown3100%
Unknown,9Pool,+1Ling250%
Unknown,9Pool,1HatchHydra1100%
Unknown,Unknown,+1Ling30%
Unknown,Unknown,1HatchLurker1100%
Unknown,Unknown,1HatchMuta1100%
Unknown,Unknown,3HatchHydra250%
Unknown,Unknown,3HatchMuta1060%
Unknown,Unknown,Unknown1173%
33 openings15761%



#8 daqin

openinggameswinsfirstlast
HatchPool,12Hatch,2HatchMuta12383%0156
PoolHatch,9Pool,2HatchMuta333%12138
PoolHatch,9Pool,3HatchMuta250%1120
PoolHatch,9Pool,6HatchHydra20%5898
PoolHatch,Overpool,2HatchMuta2378%83155
PoolHatch,Overpool,3HatchMuta30%37105
PoolHatch,Overpool,6HatchHydra10%11
7 openings15778%
enemygameswins
FFE,Forge,5GateGoon2796%
FFE,Forge,Speedlot8874%
FFE,Forge,Unknown2100%
FFE,Forge,ZealotArchon7100%
FFE,Gateway,5GateGoon250%
FFE,Gateway,Speedlot2374%
FFE,Nexus,5GateGoon2100%
FFE,Nexus,Speedlot633%
8 openings15778%


The mutalisks did in DaQin. DaQin’s slow start puts 12 hatch ahead of other choices; DaQin makes cannons before nexus regardless of what the opponent does. DaQin defends its natural entrance with cannons, but not its nexus, so the mutalisks have a free hand and DaQin finds itself short of probes.


#9 freshmeat

openinggameswinsfirstlast
PoolHatch,12Pool,2HatchMuta4065%3152
PoolHatch,12Pool,2HatchSpeedling1947%1135
PoolLair,9Pool,1HatchMuta9869%0156
3 openings15766%
enemygameswins
HatchPool,10Hatch,2HatchSpeedling2662%
HatchPool,10Hatch,3HatchMuta1338%
HatchPool,10Hatch,Unknown1060%
HatchPool,9Pool,2HatchSpeedling729%
HatchPool,9Pool,Unknown250%
HatchPool,Unknown,3HatchMuta1100%
HatchPool,Unknown,Unknown1100%
PoolHatch,4Pool,LingRush2479%
PoolHatch,9Pool,2HatchSpeedling450%
PoolHatch,9Pool,Unknown2100%
PoolHatch,Unknown,2HatchSpeedling475%
PoolHatch,Unknown,3HatchMuta1100%
PoolLair,Unknown,Unknown1100%
Unknown,9Pool,Unknown4100%
Unknown,Unknown,+1Ling2100%
Unknown,Unknown,1HatchHydra2100%
Unknown,Unknown,1HatchMuta2100%
Unknown,Unknown,3HatchMuta1164%
Unknown,Unknown,3HatchSpeedling10%
Unknown,Unknown,Unknown3967%
20 openings15766%



#10 ualbertabot

openinggameswinsfirstlast
PoolHatch,12Pool,2HatchMuta10%9898
PoolHatch,Overpool,2HatchMuta8542%0156
PoolHatch,Overpool,2HatchSpeedling7131%4154
3 openings15737%
enemygameswins
1GateCore,0Zealot,4Gate2100%
1GateCore,0Zealot,DT1100%
2Gate,10/12,ZealotRush1090%
2Gate,9/9,Unknown20%
2Gate,9/9,ZealotRush3642%
2Rax,Main,MarineRush250%
2Rax,Main,Unknown633%
PoolHatch,4Pool,LingRush5240%
RaxCC,8Rax,Unknown100%
RaxFact,Unknown,2Fact1100%
RaxFact,Unknown,Unknown10%
Unknown,Unknown,Unknown1164%
12 openings15737%


McRave met UAlbertaBot with the same strategies as last year (except for one stray PoolHatch,12Pool,2HatchMuta this year). The same strategies by name, that is. The actual play was different and performed far worse against UAlbertaBot’s pressure builds. I looked at some games. When McRave respected its enemy and defended itself, it generally won. Sometimes it seemed to arrogantly conclude “Pff, you’re not worth spending a sunken on” and got overrun. As far as I could tell from watching games, it wasn’t a scouting miss—though it’s easy to overlook things in watching games. It had the feel of a bug.

Trackbacks

No Trackbacks

Comments

No comments

Add Comment

E-Mail addresses will not be displayed and will only be used for E-Mail notifications.

To prevent automated Bots from commentspamming, please enter the string you see in the image below in the appropriate input box. Your comment will only be submitted if the strings match. Please ensure that your browser supports and accepts cookies, or your comment cannot be verified correctly.
CAPTCHA

Form options

Submitted comments will be subject to moderation before being displayed.