• Log InLog In
  • Register
Liquid`
Team Liquid Liquipedia
EDT 10:29
CEST 16:29
KST 23:29
  • Home
  • Forum
  • Calendar
  • Streams
  • Liquipedia
  • Features
  • Store
  • EPT
  • TL+
  • StarCraft 2
  • Brood War
  • Smash
  • Heroes
  • Counter-Strike
  • Overwatch
  • Liquibet
  • Fantasy StarCraft
  • TLPD
  • StarCraft 2
  • Brood War
  • Blogs
Forum Sidebar
Events/Features
News
Featured News
[ASL22] Ro8 Preview: Within Reach5[ASL22] Ro8 Preview: In A Tizzy11[ASL22] Ro16 Preview: Holy Diver5[ASL22] Ro16 Preview: Rough Waters10[ASL22] Ro24 Preview: Siren's Call8
Community News
Weekly Cups (Sept 21-27): herO and ByuN double2Weekly Cups (Sep 13-20): herO scores triple3BSL Season 2313Weekly Cups (Sep 7-12): SHIN, ByuN, MaxPax double down1StarCraft open world shooter announced at BlizzCon108
StarCraft 2
General
StarCraft open world shooter announced at BlizzCon Weekly Cups (Sept 21-27): herO and ByuN double Recent Patches and the Future Stellar Fest 1 Replay Pack Balance hotfix patch 5.0.16b (July 16)
Tourneys
2026 GSTL Grand Finals SC2 INu's Battles#21 [ 3-Days tournament ] ScienceCraft (October 24-25) - Live Event Sparkling Tuna Cup - Weekly Open Tournament Master Swan Open (Global Bronze-Master 2)
Strategy
[H] ZvP Mid-Late Game: Stalkers Collossi HT
Custom Maps
[M] (2) Sweltering Sands [M] (2) Frigid Storage
External Content
The PondCast: SC2 News & Results Mutation # 545 And Drops and Rifts Mutation # 544 Double Trouble Mutation # 543 Enhanced Defenses
Brood War
General
Where can I find Flash replays that work? Bot on ladder a Announcement on the JEDI Ringing [ASL22] Ro8 Preview: Within Reach BW General Discussion
Tourneys
[ASL22] Ro8 Day 4 [ASL22] Ro8 Day 3 [Megathread] Daily Proleagues [ASL22] Ro8 Day 2
Strategy
Cliff Jump Revisited (1 in a 1000 strategy) Replay Review Process - What do you do? Simple Questions, Simple Answers Odyssey Mineral Stack Saturation
Other Games
General Games
Warcraft III: The Frozen Throne Stormgate/Frost Giant Megathread Total Annihilation Zero Nintendo Switch Thread EVE Corporation
Dota 2
Dota 2 Champions League Season 3 Begins April 25! Official 'what is Dota anymore' discussion
League of Legends
[TL LoL EUW IHs] Teemo shall perish
Heroes of the Storm
Heroes of the Storm 2.0
Hearthstone
Deck construction bug
TL Mafia
TL Mafia Community Thread
Community
General
Things Aren’t Peaceful in Palestine US Politics Mega-thread All you football fans (soccer)! Russo-Ukrainian War Thread Artificial Intelligence Thread
Fan Clubs
MarineLorD Fan Club The Creator Fan Club The ShoWTimE Fan Club
Media & Entertainment
Movie Discussion! [Manga] One Piece Diablo Animated Series on Netflix
Sports
Football (Soccer) Thread MLB/Baseball 2023
World Cup 2022
Tech Support
Computer Build, Upgrade & Buying Resource Thread
TL Community
Recent Gifted Posts
Blogs
Violent-Cooperative Play and…
TrAiDoS
38 yo Retired SWE loo…
PurE)Rabbit-SF
Can Bots Beat Pros?? Starcr…
namkraft
[meme] I finally understa…
LUCKY_NOOB
Regacy Esports:Our Goa…
regacyesports
Customize Sidebar...

Website Feedback

Closed Threads



Active: 8493 users

BoxeR: "AlphaGo won't beat humans in StarCraft" - Page 9

Forum Index > SC2 General
568 CommentsPost a Reply
Prev 1 7 8 9 10 11 29 Next All
Grettin
Profile Joined April 2010
42416 Posts
March 13 2016 09:36 GMT
#161
On March 13 2016 18:23 rednusa wrote:
Has Google formally expressed any interest in a SC2 AI project?


Haven't seen anything but this.

"'StarCraft,' I think, is our likely next target," Google Senior Fellow Jeff Dean said at the Structure Data event in San Francisco.

Source
"If I had force-fields in Brood War, I'd never lose." -Bisu
Kerence
Profile Joined May 2011
Sweden1817 Posts
March 13 2016 09:36 GMT
#162
On March 13 2016 18:23 rednusa wrote:
Has Google formally expressed any interest in a SC2 AI project?

Apparently they have, there's already a thread about this.
http://www.teamliquid.net/forum/starcraft-2/505728-google-vs-sc2
Although reading the linked article it's not clear if they are talking about SC:BW or SC2.
http://uk.businessinsider.com/google-deepmind-could-play-starcraft-2016-3?r=US&IR=T
I am here in the shadows.
Grumbels
Profile Blog Joined May 2009
Netherlands7032 Posts
Last Edited: 2016-03-13 09:40:05
March 13 2016 09:39 GMT
#163
On March 13 2016 17:46 rabidch wrote:
it will take a while for google to come up with this though (a few years or more), mostly because of hashing out plans with blizzard (assuming theyll cooperate), designing how theyll train and do decisions, and then getting enough computing power and time to train. even with google's cloud i think it will take a massive amount of computing to train the thing, assuming they choose neutral networks like they did with alphago

Why should they need permission from Blizzard though? Their other AIs would work with just visual input, it is not like they would need access to the game state.
Well, now I tell you, I never seen good come o' goodness yet. Him as strikes first is my fancy; dead men don't bite; them's my views--amen, so be it.
Cuce
Profile Joined March 2011
Turkey1127 Posts
March 13 2016 09:56 GMT
#164
without access to game, with same control inputs given to human players, I think it will take quite a bit of time to optimize even how ai controls the game.
64K RAM SYSTEM 38911 BASIC BYTES FREE
weikor
Profile Blog Joined March 2011
Austria580 Posts
March 13 2016 09:58 GMT
#165
On March 13 2016 18:39 Grumbels wrote:
Show nested quote +
On March 13 2016 17:46 rabidch wrote:
it will take a while for google to come up with this though (a few years or more), mostly because of hashing out plans with blizzard (assuming theyll cooperate), designing how theyll train and do decisions, and then getting enough computing power and time to train. even with google's cloud i think it will take a massive amount of computing to train the thing, assuming they choose neutral networks like they did with alphago

Why should they need permission from Blizzard though? Their other AIs would work with just visual input, it is not like they would need access to the game state.


Its technically botting, and I think blizzard could sue a large conpany if they are developing illegal tools - thats why permission.

Im pretty sure an advanced Ai would crush any human player in starcraft.

Just look at those micro bots. Add perfect macro to that and they would need one build order to win 100% of games.

The advantage ai will always have In any game is 100% memory, beeing able to calculate multiple outcomes and perfect multitasking.
CrayonPopChoa
Profile Blog Joined November 2011
Canada761 Posts
March 13 2016 10:08 GMT
#166
What would be mankind's representatives for each match up?? going off of peak ELO in BW it would be

Flash vs. TZP
Jaedong vs. ZTP
Bisu vs. ZP
Jangbi/Stork vs. T
BW4LIFE
CrayonPopChoa
Profile Blog Joined November 2011
Canada761 Posts
March 13 2016 10:13 GMT
#167
On March 13 2016 17:51 Spazzer wrote:
Show nested quote +
On March 13 2016 02:38 Axieoqu wrote:
I would assume Starcraft would be even easier for the AI because mechanics are so important. Just consider how well the simple blink/micro bots work.


I think this point is the biggest issues. Here is an example of what it could accomplish and some.




but isnt that cheating, like we arent supposed to know what the siege tanks are targeting?? why would the AI know which ling is being targeted. its not like a seeker missle where it shows up alerting you. its different then like when a unit is taking damage u then micro it away. Tank shot comes without you really knowing where its gonna hit, maybe the AI could guess, but if your controlling ur tanks u can click on something else no?
BW4LIFE
Liquid`Nazgul
Profile Blog Joined September 2002
22427 Posts
Last Edited: 2016-03-13 10:21:48
March 13 2016 10:20 GMT
#168
On March 13 2016 19:13 CrayonPopChoa wrote:
Show nested quote +
On March 13 2016 17:51 Spazzer wrote:
On March 13 2016 02:38 Axieoqu wrote:
I would assume Starcraft would be even easier for the AI because mechanics are so important. Just consider how well the simple blink/micro bots work.


I think this point is the biggest issues. Here is an example of what it could accomplish and some. https://www.youtube.com/watch?v=IKVFZ28ybQs




but isnt that cheating, like we arent supposed to know what the siege tanks are targeting?? why would the AI know which ling is being targeted. its not like a seeker missle where it shows up alerting you. its different then like when a unit is taking damage u then micro it away. Tank shot comes without you really knowing where its gonna hit, maybe the AI could guess, but if your controlling ur tanks u can click on something else no?

In theory you do know which one they're going to be attacking. As a player you will know which unit will be auto-targeted first, it is just a part of the behavior of units. It isn't random. I don't think this bot knows which one they are targetting by scanning game activity files. This bot knows which one they are attacking, because yes you can determine that based on tank behavior. Professional players play around this (or should) all the time. This video is an even better example (than the marine splitting one) of why AI would totally crush any StarCraft pro given some time to learn.

I've seen some suggestions on limiting the APM and amount of clicks to be similar to mouse/keyboard input. I don't think that really matters in the end. I doubt the zergling vs. tank video has a high amount of apm involved. Even if it did you can pretty much get 90% of efficiency with just picking out individual zerglings that are going to be targeted, while the rest of your army is on a-move. It's pretty much just clicking accuracy that you can do with relatively low apms.
Administrator
KT_Elwood
Profile Joined July 2015
Germany1198 Posts
March 13 2016 10:25 GMT
#169
I think you can not make AI vs Human without apply the mechanical constraints to the AI that a Physical player has.

So I guss an AI without any restraint could easily win against any human in SC(l2). 40000 APM? Why not. Perfect macro, perfect micro and millions of games to find out the best reaction possible.
First constraint must be APM and Data Input. AI should only see the screen (Pixels), and interact through mouse/kb input.
There will be a serious task of "recognition" alone.

Easiest way: Make a robot play the game.
And I dont see a robot handel sc(2)

"First he eats our dogs, and then he taxes the penguins... Donald Trump truly is the Donald Trump of our generation. " -DPB
Liquid`Nazgul
Profile Blog Joined September 2002
22427 Posts
Last Edited: 2016-03-13 10:44:06
March 13 2016 10:29 GMT
#170
On March 13 2016 19:25 KT_Elwood wrote:
I think you can not make AI vs Human without apply the mechanical constraints to the AI that a Physical player has.

So I guss an AI without any restraint could easily win against any human in SC(l2). 40000 APM? Why not. Perfect macro, perfect micro and millions of games to find out the best reaction possible.
First constraint must be APM and Data Input. AI should only see the screen (Pixels), and interact through mouse/kb input.
There will be a serious task of "recognition" alone.

Easiest way: Make a robot play the game.
And I dont see a robot handel sc(2)


The problem is in
  • Accuracy
  • Ability to read and predict
  • No wasted clicks
  • Always 'having an eye on the screen' aka response time

I'm pretty sure you can make an absolutely crushing AI with relatively low apm (200 or so should be enough). No need to assume this AI is going to need 50k apm for the above. It will help of course it will be able to do even more, but the gains are pretty marginal since speed is one of the least important factors when you can account for the above listed points. Limiting the apm isn't going to do much.
Administrator
juvenal
Profile Joined July 2013
2448 Posts
Last Edited: 2016-03-13 10:50:56
March 13 2016 10:43 GMT
#171
On March 13 2016 15:44 Jibba wrote:
Show nested quote +
On March 13 2016 10:57 Liquid`Nazgul wrote:
On March 13 2016 10:45 Pwere wrote:
Discussing a Starcraft AI is barely better than discussing a CS:GO AI. You first need to limit the huge mechanical advantage before you can discuss what is and isn't possible.

From a purely theoretical point of view, SC is not an interesting challenge for an AI programmer/designer, so I doubt the resources will be dedicated to this for a while, and by then it won't be all that impressive.

If they plan to adapt a general AI to play Starcraft, then that is a different challenge, but the outcome still comes down to where they draw the mechanical/perceptual line.

Totally agree. It doesn't make any sense to beat top pros with limited strategy and perfect execution and then brag about it from an AI perspective. A waste of time in terms of prestige.

It would be kind of awesome to see an AI do a probe rush in BW and win with perfect micro. At least it'd be awesome the first time, and it wouldn't be awesome because of the AI but because it's such an infuriating, unsolvable way to lose.

"unsolvable", you mean no human being can rush a probe tight wall?
Michael Probu
KT_Elwood
Profile Joined July 2015
Germany1198 Posts
March 13 2016 10:49 GMT
#172
Agreed on APM cap in usefullness.
I see the problem in access on "game state" = 100% possible data in handy format and "screen/pixeldata only"
And AI with access to game state can have possible 100% flawless multitask wich will win you most Sc2 games.
If you never miss a beat, really never, then you can afford to send units out to scout everything at any time. Build 99% Depots around the map and always cancel on last sec would give you so much information. Or have 3 Reapers/lings around that give you vision on any angle of attack (on perfect micro those can always escape !). Players might not do that because they need XX minerals for BO but a computer could just scratch those XX mins from perfect Worker-Timings perfect mineral mining and so on.
I think of it as a possible 10 player Archon with mind-synchronisation.
A 10-Player Archon woul always have 100% of information possible and most of all "awareness", not only minimap-vision

"First he eats our dogs, and then he taxes the penguins... Donald Trump truly is the Donald Trump of our generation. " -DPB
Dumbledore
Profile Joined April 2011
Sweden725 Posts
March 13 2016 11:06 GMT
#173
On March 13 2016 18:58 weikor wrote:
Show nested quote +
On March 13 2016 18:39 Grumbels wrote:
On March 13 2016 17:46 rabidch wrote:
it will take a while for google to come up with this though (a few years or more), mostly because of hashing out plans with blizzard (assuming theyll cooperate), designing how theyll train and do decisions, and then getting enough computing power and time to train. even with google's cloud i think it will take a massive amount of computing to train the thing, assuming they choose neutral networks like they did with alphago

Why should they need permission from Blizzard though? Their other AIs would work with just visual input, it is not like they would need access to the game state.


Its technically botting, and I think blizzard could sue a large conpany if they are developing illegal tools - thats why permission.

Im pretty sure an advanced Ai would crush any human player in starcraft.

Just look at those micro bots. Add perfect macro to that and they would need one build order to win 100% of games.

The advantage ai will always have In any game is 100% memory, beeing able to calculate multiple outcomes and perfect multitasking.



You really think botting in games is illegal? lol
Have a nice day ;)
404AlphaSquad
Profile Joined October 2011
839 Posts
March 13 2016 11:15 GMT
#174
I am on team Human
aka Kalevi
Charoisaur
Profile Joined August 2014
Germany16095 Posts
March 13 2016 11:27 GMT
#175
On March 13 2016 19:20 Liquid`Nazgul wrote:
Show nested quote +
On March 13 2016 19:13 CrayonPopChoa wrote:
On March 13 2016 17:51 Spazzer wrote:
On March 13 2016 02:38 Axieoqu wrote:
I would assume Starcraft would be even easier for the AI because mechanics are so important. Just consider how well the simple blink/micro bots work.


I think this point is the biggest issues. Here is an example of what it could accomplish and some. https://www.youtube.com/watch?v=IKVFZ28ybQs




but isnt that cheating, like we arent supposed to know what the siege tanks are targeting?? why would the AI know which ling is being targeted. its not like a seeker missle where it shows up alerting you. its different then like when a unit is taking damage u then micro it away. Tank shot comes without you really knowing where its gonna hit, maybe the AI could guess, but if your controlling ur tanks u can click on something else no?

In theory you do know which one they're going to be attacking. As a player you will know which unit will be auto-targeted first, it is just a part of the behavior of units. It isn't random. I don't think this bot knows which one they are targetting by scanning game activity files. This bot knows which one they are attacking, because yes you can determine that based on tank behavior. Professional players play around this (or should) all the time. This video is an even better example (than the marine splitting one) of why AI would totally crush any StarCraft pro given some time to learn.

I've seen some suggestions on limiting the APM and amount of clicks to be similar to mouse/keyboard input. I don't think that really matters in the end. I doubt the zergling vs. tank video has a high amount of apm involved. Even if it did you can pretty much get 90% of efficiency with just picking out individual zerglings that are going to be targeted, while the rest of your army is on a-move. It's pretty much just clicking accuracy that you can do with relatively low apms.

really? always box-clicking the zerglings surrounding the targeted zergling and individually pulling them away and that multiple times at once. I'm pretty sure the APM are insane in that scenario.
Many of the coolest moments in sc2 happen due to worker harassment
moonlawn
Profile Joined May 2010
Latvia6 Posts
March 13 2016 11:33 GMT
#176
now say it to AUTOMATON 2000



Liquid`Nazgul
Profile Blog Joined September 2002
22427 Posts
March 13 2016 11:34 GMT
#177
On March 13 2016 20:27 Charoisaur wrote:
Show nested quote +
On March 13 2016 19:20 Liquid`Nazgul wrote:
On March 13 2016 19:13 CrayonPopChoa wrote:
On March 13 2016 17:51 Spazzer wrote:
On March 13 2016 02:38 Axieoqu wrote:
I would assume Starcraft would be even easier for the AI because mechanics are so important. Just consider how well the simple blink/micro bots work.


I think this point is the biggest issues. Here is an example of what it could accomplish and some. https://www.youtube.com/watch?v=IKVFZ28ybQs




but isnt that cheating, like we arent supposed to know what the siege tanks are targeting?? why would the AI know which ling is being targeted. its not like a seeker missle where it shows up alerting you. its different then like when a unit is taking damage u then micro it away. Tank shot comes without you really knowing where its gonna hit, maybe the AI could guess, but if your controlling ur tanks u can click on something else no?

In theory you do know which one they're going to be attacking. As a player you will know which unit will be auto-targeted first, it is just a part of the behavior of units. It isn't random. I don't think this bot knows which one they are targetting by scanning game activity files. This bot knows which one they are attacking, because yes you can determine that based on tank behavior. Professional players play around this (or should) all the time. This video is an even better example (than the marine splitting one) of why AI would totally crush any StarCraft pro given some time to learn.

I've seen some suggestions on limiting the APM and amount of clicks to be similar to mouse/keyboard input. I don't think that really matters in the end. I doubt the zergling vs. tank video has a high amount of apm involved. Even if it did you can pretty much get 90% of efficiency with just picking out individual zerglings that are going to be targeted, while the rest of your army is on a-move. It's pretty much just clicking accuracy that you can do with relatively low apms.

really? always box-clicking the zerglings surrounding the targeted zergling and individually pulling them away and that multiple times at once. I'm pretty sure the APM are insane in that scenario.

I mean sure it isn't a walk in the park, but for a computer with perfect accuracy I don't think it needs to be abnormally high to get a high reward. You can continue to make it better to pretty much unlimited apm, though. Essentially pulling away zerglings and selecting single zerglings with perfect accuracy should be doable while keeping the numbers low.
Administrator
outscar
Profile Joined September 2014
2832 Posts
Last Edited: 2016-03-13 11:44:20
March 13 2016 11:42 GMT
#178
The Emperor has spoken so Google needs to look up some other things. He gonna bunker rush x3 and score gonna be 3-0. If AlphaGo risks then we gonna get new pimpest play where BoxeR humiliates the machine, hell it's about damn time.
sunbeams are never made like me...
Fighter
Profile Joined August 2010
Korea (South)1531 Posts
Last Edited: 2016-03-13 11:52:57
March 13 2016 11:48 GMT
#179
Has anyone posted any links to some of those micro bots? I remember one where lings were micro'd perfectly against tanks, so each tank shot only one died. Made lings look ungodly powerful.

edit: OH. Yep, it's on this page :p
For Aiur???
Charoisaur
Profile Joined August 2014
Germany16095 Posts
March 13 2016 11:51 GMT
#180
On March 13 2016 20:48 Fighter wrote:
Has anyone posted any links to some of those micro bots? I remember one where lings were micro'd perfectly against tanks, so each tank shot only one died. Made lings look ungodly powerful.

no, here aren't any links...
Many of the coolest moments in sc2 happen due to worker harassment
Prev 1 7 8 9 10 11 29 Next All
Please log in or register to reply.
Live Events Refresh
Next event in 9h 31m
[ Submit Event ]
Live Streams
Refresh
StarCraft 2
ProTech144
Codebar 14
StarCraft: Brood War
Leta 2231
EffOrt 1051
Soma 827
Mini 796
ggaemo 406
Horang2 376
Light 352
Rush 350
BeSt 313
Stork 285
[ Show more ]
Larva 275
Snow 239
actioN 182
hero 179
Barracks 165
Killer 138
firebathero 116
Zeus 103
Sea.KH 71
JYJ 67
Mong 55
Aegong 47
Sharp 46
Sexy 39
Shinee 36
ToSsGirL 35
Bale 25
zelot 21
sorry 18
Terrorterran 17
Rock 14
Shine 13
Sacsri 10
Icarus 9
JulyZerg 8
Dewaltoss 4
Dota 2
Gorgc7158
qojqva1546
Dendi825
XaKoH 464
420jenkins49
Counter-Strike
Fnx 673
kRYSTAL_461
edward79
Heroes of the Storm
crisheroes4634
Khaldor375
Other Games
gofns47547
singsing1739
B2W.Neo868
byalli544
Lowko421
DeMusliM216
mouzStarbuck190
Liquid`VortiX161
Livibee144
ArmadaUGS108
KnowMe101
Chillindude16
Railgan14
amsayoshi14
Organizations
Other Games
WardiTV279
BasetradeTV185
Dota 2
PGL Dota 2 - Main Stream165
[ Show 16 non-featured ]
StarCraft 2
• StrangeGG 69
• mYiSmile119
• intothetv
• AfreecaTV YouTube
• Kozan
• IndyKCrew
• Migwel
StarCraft: Brood War
• HerbMon 27
• FirePhoenix6
• BSLYoutube
• STPLYoutube
• ZZZeroYoutube
Dota 2
• WagamamaTV372
League of Legends
• Nemesis2126
• Jankos1856
• TFBlade575
Upcoming Events
PiGosaur Cup
9h 31m
Kung Fu Cup
20h 31m
The PondCast
1d 19h
OSC
1d 22h
Replay Cast
2 days
CranKy Ducklings
3 days
Online Event
3 days
FEL
4 days
AI Arena Tournament
4 days
BSL: Ladder Tournament
4 days
[ Show More ]
Sparkling Tuna Cup
4 days
BSL Open Qualifier
5 days
BSL Open Qualifier
5 days
WardiTV Weekly
5 days
Liquipedia Results

Completed

Proleague 2026-09-27
Blizzard Classic Cup 2026
Calamity Invitational

Ongoing

ASL Season 22
Super Anchor Qualifying S3
CSL 2026 AUTUMN (S22)
Acropolis #5
1win Private Club #1
Logitech G Play Connect 2026
SL StarSeries Fall 2026
FISSURE Playground #3
BLAST Open Fall 2026
Esports World Cup 2026
BLAST Bounty Summer 2026
BLAST Bounty Summer Qual
Stake Ranked Episode 3

Upcoming

Acropolis #5 - GSB
Acropolis #5 - GSC
BSL Season 23
SC4ALL II: Brood War
BSL 23: Non-Korean Championship
HSC XXX
Stellar Fest 2: Lunar Cup
SC4ALL II: StarCraft II
Kung Fu Cup 2026 Grand Finals
RSL Offline Finals
Custodian Cup
Copium Cup
PGL Major Singapore 2026
Stake Ranked Episode 6
BLAST Rivals Fall 2026
IEM Beijing 2026
Stake Ranked Episode 5
PGL Masters Bucharest 2026
1win Private Club #2
Thunderpick World Champ. '26
ESL Pro League Season 24
Stake Ranked Episode 4
TLPD

1. ByuN
2. TY
3. Dark
4. Solar
5. Stats
6. Nerchio
7. sOs
8. soO
9. INnoVation
10. Elazer
1. Rain
2. Flash
3. EffOrt
4. Last
5. Bisu
6. Soulkey
7. Mini
8. Sharp
Sidebar Settings...

Advertising | Privacy Policy | Terms Of Use | Contact Us

Original banner artwork: Jim Warren
The contents of this webpage are copyright © 2026 TLnet. All Rights Reserved.