• Log InLog In
  • Register
Liquid`
Team Liquid Liquipedia
EDT 13:44
CEST 19:44
KST 02:44
  • 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
ByuL, and the Limitations of Standard Play3Team Liquid Map Contest #22: Results and Winners7Code S Season 2 (2026): RO4 and Finals Preview12TL.net Map Contest #22 - Voting & Ladder Map Selection7Code S Season 2 (2026) - RO8 Preview8
Community News
MC vs IdrA, Boxer vs Nal_rA to be Legacy Matches @ BlizzCon175.0.16 Hotfix (June 30) - Balance + Bug Fixes21Weekly Cups (June 22-28): Zergs thrive in new patch2[TLMC] Summer 2026 Ladder Map Rotation05.0.16 patch for SC2 goes live (8 worker start)99
StarCraft 2
General
5.0.16 Hotfix (June 30) - Balance + Bug Fixes MC vs IdrA, Boxer vs Nal_rA to be Legacy Matches @ BlizzCon 5.0.16 patch for SC2 goes live (8 worker start) Is the larve respawn broken? ByuL, and the Limitations of Standard Play
Tourneys
RSL Revival: Season 6 - Qualifiers and Main Event Douyu Cup 2026: $20,000 Legends Event (June 26-28) Maestros of The Game 2 announcement and schedule ! INu's Battles#17 <BO.9> Sparkling Tuna Cup - Weekly Open Tournament
Strategy
[G] Having the right mentality to improve
Custom Maps
New Map Maker - Looking for Advice - Love or Hate Work In Progress Melee Maps [D]RTS in all its shapes and glory <3
External Content
The PondCast: SC2 News & Results Mutation # 532 Nuclear Family Mutation # 531 Experimental Artillery Mutation # 530 One For All
Brood War
General
ASL 22 Proposed Map Pool Starcraft vs Retro Category on Twitch ProGamer Paychecks Story BW General Discussion Best thing happen to StarCraft since Remastered?
Tourneys
[Megathread] Daily Proleagues [ASL21] Grand Finals The Casual Games of the Week Thread [BSL22] GosuLeague Casts - Tue & Thu 22:00 CEST
Strategy
Simple Questions, Simple Answers Creating a full chart of Zerg builds Relatively freeroll strategies Why doesn't anyone use restoration?
Other Games
General Games
ZeroSpace at Steam NextFest - Last free demo Nintendo Switch Thread Path of Exile Stormgate/Frost Giant Megathread Beyond All Reason
Dota 2
Looking for a Dota Mentor Official 'what is Dota anymore' discussion
League of Legends
Heroes of the Storm
Simple Questions, Simple Answers Heroes of the Storm 2.0
Hearthstone
Deck construction bug
TL Mafia
[94721]Better Good-Health Signs Than 3-15 Bans/Yea TL Mafia Community Thread Vanilla Mini Mafia
Community
General
US Politics Mega-thread Russo-Ukrainian War Thread Men's Fashion Thread Canadian Politics Mega-thread The Games Industry And ATVI
Fan Clubs
The HerO Fan Club! The herO Fan Club!
Media & Entertainment
Movie Discussion! Series you have seen recently... [Req][Books] Good Fantasy/SciFi books [TV/BOOK] *SPOILERS* Game of Thrones Discussion
Sports
2024 - 2026 Football Thread TeamLiquid Health and Fitness Initiative For 2023 Formula 1 Discussion McBoner: A hockey love story Cricket [SPORT]
World Cup 2022
Tech Support
How to clean a TTe Thermaltake keyboard? Computer Build, Upgrade & Buying Resource Thread
TL Community
The Automated Ban List
Blogs
Listen To The Coaches!
TrAiDoS
An Exploration of th…
waywardstrategy
I'm an arrogant trash talke…
FlaShFTW
Gauntlet SC2: A Retrospectiv…
Ctone23
ramps on octagon
StaticNine
Funny Nicknames
LUCKY_NOOB
Evil Gacha Games and the…
ffswowsucks
Customize Sidebar...

Website Feedback

Closed Threads



Active: 4900 users

BoxeR: "AlphaGo won't beat humans in StarCraft" - Page 17

Forum Index > SC2 General
568 CommentsPost a Reply
Prev 1 15 16 17 18 19 29 Next All
necaremus
Profile Joined December 2013
45 Posts
March 15 2016 21:05 GMT
#321
On March 16 2016 04:45 Xyik wrote:
[...] divide that by the 9 possible match-ups (TvX, ZvX, PvX), [...]

try that again, plz >_>

unless you are counting TvZ and ZvT as different match-up, i don't get 9
“Never assume malice when stupidity will suffice.”
Xyik
Profile Blog Joined November 2009
Canada728 Posts
March 15 2016 21:25 GMT
#322
On March 16 2016 06:05 necaremus wrote:
Show nested quote +
On March 16 2016 04:45 Xyik wrote:
[...] divide that by the 9 possible match-ups (TvX, ZvX, PvX), [...]

try that again, plz >_>

unless you are counting TvZ and ZvT as different match-up, i don't get 9


i was thinking that it would need to learn the play Z build orders vs T just as it would need to learn to play T orders vs Z, but yes you are right, you can remove all duplicates by segmentation (e.g: treat a TvZ same as a ZvT when the map, spawn and build orders are the same for both races).
LetaBot
Profile Blog Joined June 2014
Netherlands557 Posts
March 15 2016 22:17 GMT
#323
Technically there already is an APM limit in Brood War. In one of the games my bot played today, no units where being produced because some units were spamming so much apm that the network buffer got full.

I have also seen several bots that let their units spam so much apm that they keep getting stuck in the attack animation without actually attacking.


As for limiting the apm to something like 300: Once bots can defeat pro-players without an APM limit rule, you can slowly start capping it more and more. Right now bots are only competitive with C- or lower players, even with their high apm.
If you cannot win with 100 apm, win with 100 cpm.
snakeeyez
Profile Joined May 2011
United States1231 Posts
March 15 2016 22:47 GMT
#324
I think brood war would be a mighty big test for AI, and I do think if these researchers pick starcraft as a proving ground they will far surpass all existing bots and show new tech that might beat the likes of flash or jaedong.
That being said a bot playing protoss could beat pro human players just with perfect dragoon micro and kiting. It would always trade favorably, and then just win late game with all those advantages. Its not really fair if flash has to either micro marines or macro at his base while the bot can do everything at once. Its a huge advantage for the bot.
Making a bot that beats flash in a best of 7 without falling into predictable patterns or stupid build orders/decisions would be a very tough AI challenge though. Even harder if you emulate how a human plays the game so it has to beat him fairly. After beating GO grandmaster they are running out of games to solve honestly. I never thought they would win at GO its something they been after since 1960s
dankobanana
Profile Joined February 2016
Croatia244 Posts
March 15 2016 22:49 GMT
#325
maybe it already on bnet as IIIIIIIIIIII
Battle is waged in the name of the many. The brave, who generation after generation choose the mantle of - Dark Templar!
Charoisaur
Profile Joined August 2014
Germany16081 Posts
Last Edited: 2016-03-16 00:43:42
March 16 2016 00:40 GMT
#326
On March 16 2016 04:40 nimdil wrote:
It's funny that people discuss - at the same time - if AI could beat top players in StarCraft and the ways how SC-tuned AlphaGo like AI (so AlphaSC I guess) should be obstructed so that the game will be fair.

AlphaGo is an AI that bases it's aactions on graphical input and that's it. If you feel that you need to tune down the ability of AI to execute perfect strategies at superhuman speed even though it would be using standard inputs then sorry but it is game over. AI won.

SC2 is meant to be played with mechanical restraints (aka mouse and keyboard) and not through graphical input.
If someone plays sc2 without those mechanical restraints he would be basically cheating.
So the only fair ways for an AI vs human game would be either to have the AI played by a robot (which isn't technically possible) or simulate a robot (aka played through graphical input but with the mechanical restraints that humans/robots have).
otherwise the AI would be cheating.
Many of the coolest moments in sc2 happen due to worker harassment
LetaBot
Profile Blog Joined June 2014
Netherlands557 Posts
March 16 2016 01:47 GMT
#327
On March 16 2016 09:40 Charoisaur wrote:
Show nested quote +
On March 16 2016 04:40 nimdil wrote:
It's funny that people discuss - at the same time - if AI could beat top players in StarCraft and the ways how SC-tuned AlphaGo like AI (so AlphaSC I guess) should be obstructed so that the game will be fair.

AlphaGo is an AI that bases it's aactions on graphical input and that's it. If you feel that you need to tune down the ability of AI to execute perfect strategies at superhuman speed even though it would be using standard inputs then sorry but it is game over. AI won.

SC2 is meant to be played with mechanical restraints (aka mouse and keyboard) and not through graphical input.
If someone plays sc2 without those mechanical restraints he would be basically cheating.
So the only fair ways for an AI vs human game would be either to have the AI played by a robot (which isn't technically possible) or simulate a robot (aka played through graphical input but with the mechanical restraints that humans/robots have).
otherwise the AI would be cheating.



So to clarify, would this be considered cheating or not by you?


If you cannot win with 100 apm, win with 100 cpm.
Hexe
Profile Joined August 2014
United States332 Posts
March 16 2016 04:06 GMT
#328
It would be impossible for an AI to beat someone at SC2 let alone SCBW. mind games are a real thing. bo7 absolutely no way. I can see one build. one matchup. one race. but even that someone can cheese and think of something that another person cant
Baarn
Profile Joined April 2010
United States2702 Posts
Last Edited: 2016-03-16 05:03:34
March 16 2016 05:01 GMT
#329
Boxer will get smashed by a bot at alphago's level and funding. He'd be out of his league in micro/macro and even scouting. People are trying to debate that "mind games" are going to turn the tide. With a little ai adjustment it will be able scout twice before really committing to a build. Maybe even more as the ai improves? You have to think that an ai can simultaneously look around the map while building units, expanding, moving workers etc. Asinine to think humans will have any advantage when you will be constantly behind from the first second the game starts.
There's no S in KT. :P
aTnClouD
Profile Blog Joined May 2007
Italy2428 Posts
March 16 2016 06:14 GMT
#330
Bots are nowhere near the level to solve starcraft and play the best players. Don't underestimate the complexity and amount of time of learning Starcraft through trial and error for a computer compared to a game like chess. There's too much difference between the two and human brain can still find valid strategies at a higher and faster degree than a bot at this point in time.
http://i53.photobucket.com/albums/g64/hunter692007/kruemelmonsteryn0.gif
ashara
Profile Joined July 2008
France22 Posts
March 16 2016 07:53 GMT
#331
Quite exciting to see they may tackle Starcraft after Go. I don't think AIs are anywhere close to beat top SC players yet, but if they put the money and effort I expect it to happen at some point. Although maybe not with close to 100% winrate though, because build order losses may still happen.

It would be quite interesting to see if they can make an AI that just knows how to learn. So that you could tell it: "learn to play Starcraft 1v1 at top level" or "write an html5 breakout game and publish it on this platform" and it would actually do it.
papaz
Profile Joined December 2009
Sweden4149 Posts
Last Edited: 2016-03-16 08:05:13
March 16 2016 08:04 GMT
#332
On March 16 2016 15:14 aTnClouD wrote:
Bots are nowhere near the level to solve starcraft and play the best players. Don't underestimate the complexity and amount of time of learning Starcraft through trial and error for a computer compared to a game like chess. There's too much difference between the two and human brain can still find valid strategies at a higher and faster degree than a bot at this point in time.


I think in GO the AI learnt by playing literally millions of games vs itself.

It would do the same thing in Starcraft in order to improve, just as humans do. The only difference? It can play millions of games simultaneously and learn faster than any human.

Also it could learn the game by "watching" vods of pro players.

There is no possible way a human can come close to computers. Just think about it for a second. Just 40 years ago there was no home PCs.

Today we have computers everywhere, in just 40 years!

Just think of how fast the development goes. Can you even imagine the world in 40 more years from today?

If Google decides to dedicate time to a Starcrat AI make no mistake. It will crush any of todays pros. I love how the pro GO players were so confident of themselves and both European and World champion got crushed.

Google and AI fighting!

aTnClouD
Profile Blog Joined May 2007
Italy2428 Posts
March 16 2016 09:29 GMT
#333
On March 16 2016 17:04 papaz wrote:
Show nested quote +
On March 16 2016 15:14 aTnClouD wrote:
Bots are nowhere near the level to solve starcraft and play the best players. Don't underestimate the complexity and amount of time of learning Starcraft through trial and error for a computer compared to a game like chess. There's too much difference between the two and human brain can still find valid strategies at a higher and faster degree than a bot at this point in time.


I think in GO the AI learnt by playing literally millions of games vs itself.

It would do the same thing in Starcraft in order to improve, just as humans do. The only difference? It can play millions of games simultaneously and learn faster than any human.

Also it could learn the game by "watching" vods of pro players.

There is no possible way a human can come close to computers. Just think about it for a second. Just 40 years ago there was no home PCs.

Today we have computers everywhere, in just 40 years!

Just think of how fast the development goes. Can you even imagine the world in 40 more years from today?

If Google decides to dedicate time to a Starcrat AI make no mistake. It will crush any of todays pros. I love how the pro GO players were so confident of themselves and both European and World champion got crushed.

Google and AI fighting!


As I previously stated bots are not capable of competing with humans at this point in time. There will be a point in the future when they will solve any kind of complex game but the day is not close to now. It comes down to how complex the game is. Backgammon has been solved but poker is nowhere close to be solved. Starcraft is extraordinarily complex and so the same applies for it. As computers get better and faster and better self learning programs are developed sure AI will find and execute strategies that can't be overcome by humans.
http://i53.photobucket.com/albums/g64/hunter692007/kruemelmonsteryn0.gif
sh1RoKen
Profile Joined March 2012
Russian Federation93 Posts
March 16 2016 11:11 GMT
#334
On March 16 2016 18:29 aTnClouD wrote:
Show nested quote +
On March 16 2016 17:04 papaz wrote:
On March 16 2016 15:14 aTnClouD wrote:
Bots are nowhere near the level to solve starcraft and play the best players. Don't underestimate the complexity and amount of time of learning Starcraft through trial and error for a computer compared to a game like chess. There's too much difference between the two and human brain can still find valid strategies at a higher and faster degree than a bot at this point in time.


I think in GO the AI learnt by playing literally millions of games vs itself.

It would do the same thing in Starcraft in order to improve, just as humans do. The only difference? It can play millions of games simultaneously and learn faster than any human.

Also it could learn the game by "watching" vods of pro players.

There is no possible way a human can come close to computers. Just think about it for a second. Just 40 years ago there was no home PCs.

Today we have computers everywhere, in just 40 years!

Just think of how fast the development goes. Can you even imagine the world in 40 more years from today?

If Google decides to dedicate time to a Starcrat AI make no mistake. It will crush any of todays pros. I love how the pro GO players were so confident of themselves and both European and World champion got crushed.

Google and AI fighting!


As I previously stated bots are not capable of competing with humans at this point in time. There will be a point in the future when they will solve any kind of complex game but the day is not close to now. It comes down to how complex the game is. Backgammon has been solved but poker is nowhere close to be solved. Starcraft is extraordinarily complex and so the same applies for it. As computers get better and faster and better self learning programs are developed sure AI will find and execute strategies that can't be overcome by humans.


Could you please read about AlphaGo or Artificial neural networks just a little bit before arguing about the topic you clearly know nothing about. That "point in the future when they will solve any kind of complex game" has been reached just now. GO has more combinations than atoms in the whole universe. And that AI doesn't calculated all of it and solved the whole game. He learned to play the game like humans do but much better. That AI has nothing in common with any other AI you might find in any other game.

And BTW:
1. He can kill 100 mutalisks with 1 phoenix without taking any damage
2. He can kill 200 marines without steam with 1 stalker without taking any damage
3. He can kill 33 ultralisks with 1 immortal + warp prism without taking any damage
4. He can do 1, 2 and 3 at the same time.

Starcraft units wasn't designed to be microed by computer.
Be polite, be professional, but have a plan to kill everybody you meet.
Poopi
Profile Blog Joined November 2010
France12971 Posts
March 16 2016 12:59 GMT
#335
You realize AlphaGO isn't an ordinary neural network right?

The success of Alpha GO or how neural networks work don't mean it's an insta gg, far from it.

The fact that SC depends so much on mechanics is a problem because you have to balance it, not because we want a "fair" match but because the point is to have an AI that does well in such a complex game strategically, but a lot of its complexity lies in the interface we have to use.
WriterMaru
Flonomenalz
Profile Joined May 2011
Nigeria3519 Posts
March 16 2016 13:23 GMT
#336
Without limitations on the APM or something... I don't see how any pro beats AI. SC units commanded by a computer are totally unfair. Perfectly micro'd units? Lol.

I think the only way to beat it would be to come at it with a strategy it had never seen before? But even then...
I love crazymoving
nimdil
Profile Blog Joined January 2011
Poland3765 Posts
March 16 2016 14:32 GMT
#337
On March 16 2016 09:40 Charoisaur wrote:
Show nested quote +
On March 16 2016 04:40 nimdil wrote:
It's funny that people discuss - at the same time - if AI could beat top players in StarCraft and the ways how SC-tuned AlphaGo like AI (so AlphaSC I guess) should be obstructed so that the game will be fair.

AlphaGo is an AI that bases it's aactions on graphical input and that's it. If you feel that you need to tune down the ability of AI to execute perfect strategies at superhuman speed even though it would be using standard inputs then sorry but it is game over. AI won.

SC2 is meant to be played with mechanical restraints (aka mouse and keyboard) and not through graphical input.
If someone plays sc2 without those mechanical restraints he would be basically cheating.
So the only fair ways for an AI vs human game would be either to have the AI played by a robot (which isn't technically possible) or simulate a robot (aka played through graphical input but with the mechanical restraints that humans/robots have).
otherwise the AI would be cheating.

To be fair it's just the most efficient way for Humans to interact but if we could prepare mouse, keyboard and mechanical hands (jesus that's stupid already) that yet would be able to spam on the level of thousand of actions per minute (obviously it would be custom build mouse and keyboard) - would it be "fair"? Because I don't think it'd be too hard compared to how complicated is building AI like alphago. What you would be doing is encorcing trnaslation of eletronic impulses into mechanical moves which in turn will be translated into other elektronic impuulses.
I call it stupid.
Crying
Profile Joined February 2011
Bulgaria778 Posts
March 16 2016 15:13 GMT
#338
As a programmer, player and so on i have something to say.

AlphaGo utilizes Machine Learning specifically to learn to play the game through numerous amounts of data.

Imagine feeding AlphaGo with good amount of data (replays), where he can study and create absolutely beautiful results.

The difference between chess go and starcraft is that chess and go is the following :

Chess uses heuristics to provide the best move.
Go uses heavy machine learning and neural networks to study games and thus come with best move/strategy
Starcraft would have to use machine learning neural networks AND heuristics probably to achieve better results, also it needs huge quantity of data.

The thing is, chess at the moment is pretty much absolutely dominated by computers, Magnus Carlsen for instance having an ELO of 2850~, a computer easiliy pulls 3000+, even going to 3300 with different settings.
The best outcome Magnus has versus a computer is that of a draw. Chess grandmasters say they use engines to evaluate situations and see their mistakes in matches, most of them never play enginges because its pointless, while u see 20moves ahead, the engine already calculated more than 10 million. And due to the heuristic based search, it will always minimize your outcome with minimax algorithm, clever alpha-beta pruning, quintessence search and so on.

Starcraft however hasn't got perfect information, thus searching is not possible, to some extent however. The amount of advancement in Machine Learning, Neural Networks and so on in the past years will probably some day bring an abomination to life. At the moment people don't really know how to make A.I. safe.(for humans)

It blows my mind how in 1960's we didn't even know how to find the shortest path from A-B and nowadays we have these things.
Determination~ Hard Work Surpass NATURAL GENIUS!
heqat
Profile Joined October 2011
Switzerland96 Posts
March 16 2016 16:13 GMT
#339
Next level AI could use a synthetic brain such as the Blue Brain:

https://en.wikipedia.org/wiki/Blue_Brain_Project
rockslave
Profile Blog Joined January 2008
Brazil318 Posts
March 16 2016 17:21 GMT
#340
It blows my mind how in 1960's we didn't even know how to find the shortest path from A-B and nowadays we have these things.


https://en.wikipedia.org/wiki/Dijkstra's_algorithm =P
What qxc said.
Prev 1 15 16 17 18 19 29 Next All
Please log in or register to reply.
Live Events Refresh
Next event in 6h 16m
[ Submit Event ]
Live Streams
Refresh
StarCraft 2
RushiSC 113
BRAT_OK 72
MindelVK 17
StarCraft: Brood War
Britney 17985
EffOrt 923
BeSt 239
ggaemo 236
Dewaltoss 108
Zeus 61
Pusan 45
sorry 29
Mong 29
Free 29
[ Show more ]
scan(afreeca) 25
Rock 18
zelot 17
Bale 16
Sacsri 10
Shine 10
Dota 2
qojqva1837
420jenkins245
LuMiX1
Counter-Strike
fl0m1651
x6flipin738
edward87
adren_tv81
kRYSTAL_9
Other Games
Grubby2096
FrodaN1182
B2W.Neo955
Dendi646
Beastyqt549
RotterdaM329
C9.Mang0189
KnowMe123
UpATreeSC59
Trikslyr44
Mew2King42
JuggernautJason24
Organizations
Dota 2
PGL Dota 2 - Main Stream199
StarCraft 2
Blizzard YouTube
StarCraft: Brood War
BSLTrovo
[ Show 17 non-featured ]
StarCraft 2
• IndyKCrew
• sooper7s
• AfreecaTV YouTube
• Migwel
• intothetv
• LaughNgamezSOOP
• Kozan
StarCraft: Brood War
• 80smullet 15
• FirePhoenix4
• STPLYoutube
• ZZZeroYoutube
• BSLYoutube
League of Legends
• Nemesis2884
• TFBlade816
Other Games
• imaqtpie435
• Shiphtur377
• tFFMrPink 11
Upcoming Events
Replay Cast
6h 16m
CrankTV Team League
17h 16m
Bombastic Starleague
1d 2h
The PondCast
1d 16h
HomeStory Cup
1d 17h
Replay Cast
2 days
HomeStory Cup
2 days
Replay Cast
3 days
HomeStory Cup
3 days
OSC
3 days
[ Show More ]
Sparkling Tuna Cup
4 days
WardiTV Weekly
5 days
The PondCast
6 days
Liquipedia Results

Completed

YSL S3
Douyu Cup 2026
Murky Cup 2026

Ongoing

IPSL Spring 2026
Acropolis #4
CSL Season 21: Qualifier 2
SCTL 2026 Spring
XSE Pro League 2026
IEM Cologne Major 2026
Stake Ranked Episode 2
CS Asia Championships 2026
Asian Champions League 2026
IEM Atlanta 2026
PGL Astana 2026
BLAST Rivals Spring 2026
IEM Rio 2026

Upcoming

CSL 2026 Summer (S21)
ASL Season 22:Wild Card Qualifier
CSLAN 4
Blizzard Classic Cup 2026
Kung Fu Cup 2026 Grand Finals
RSL Revival: Season 6
CranK Gathers Season 4: BW vs SC2 Team League
HSC XXIX
Light Tournament 2026
Eternal Conflict S2 Finale
Heroes Pulsing #3
Eternal Conflict S2 E1
FISSURE Playground #5
BLAST Open Fall 2026
Esports World Cup 2026
BLAST Bounty Summer 2026
BLAST Bounty Summer Qual
Stake Ranked Episode 3
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.