• Log InLog In
  • Register
Liquid`
Team Liquid Liquipedia
EDT 23:27
CEST 05:27
KST 12:27
  • 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
TL Team Map Contest #5: Presented by Monster Energy2Code S RO8 Preview: herO, Zoun, Bunny, Classic7Code S RO8 Preview: Rogue, GuMiho, Solar, Maru3BGE Stara Zagora 2025: Info & Preview27Code S RO12 Preview: GuMiho, Bunny, SHIN, ByuN3
Community News
Code S RO8 Results + RO4 Bracket (2025 Season 2)3BGE Stara Zagora 2025 - Replay Pack2Weekly Cups (June 2-8): herO doubles down1[BSL20] ProLeague: Bracket Stage & Dates9GSL Ro4 and Finals moved to Sunday June 15th13
StarCraft 2
General
How herO can make history in the Code S S2 finals TL Team Map Contest #5: Presented by Monster Energy Code S RO8 Results + RO4 Bracket (2025 Season 2) Jim claims he and Firefly were involved in match-fixing The SCII GOAT: A statistical Evaluation
Tourneys
[GSL 2025] Code S: Season 2 - Ro8 - Group A [GSL 2025] Code S: Season 2 - Ro8 - Group B RSL: Revival, a new crowdfunded tournament series SOOPer7s Showmatches 2025 Sparkling Tuna Cup - Weekly Open Tournament
Strategy
[G] Darkgrid Layout Simple Questions Simple Answers [G] PvT Cheese: 13 Gate Proxy Robo
Custom Maps
[UMS] Zillion Zerglings
External Content
Mutation # 477 Slow and Steady Mutation # 476 Charnel House Mutation # 475 Hard Target Mutation # 474 Futile Resistance
Brood War
General
BW General Discussion BGH auto balance -> http://bghmmr.eu/ FlaSh Witnesses SCV Pull Off the Impossible vs Shu StarCraft & BroodWar Campaign Speedrun Quest Will foreigners ever be able to challenge Koreans?
Tourneys
[BSL20] ProLeague Bracket Stage - Day 4 [BSL20] ProLeague Bracket Stage - Day 3 [Megathread] Daily Proleagues [ASL19] Grand Finals
Strategy
I am doing this better than progamers do. [G] How to get started on ladder as a new Z player
Other Games
General Games
Stormgate/Frost Giant Megathread Path of Exile Nintendo Switch Thread Beyond All Reason What do you want from future RTS games?
Dota 2
Official 'what is Dota anymore' discussion
League of Legends
Who’s Getting the Effortless-Chic Look Just Right?
Heroes of the Storm
Simple Questions, Simple Answers Heroes of the Storm 2.0
Hearthstone
Heroes of StarCraft mini-set
TL Mafia
TL Mafia Community Thread Vanilla Mini Mafia
Community
General
Things Aren’t Peaceful in Palestine US Politics Mega-thread UK Politics Mega-thread Russo-Ukrainian War Thread Vape Nation Thread
Fan Clubs
Maru Fan Club Serral Fan Club
Media & Entertainment
Korean Music Discussion [Manga] One Piece
Sports
TeamLiquid Health and Fitness Initiative For 2023 2024 - 2025 Football Thread Formula 1 Discussion NHL Playoffs 2024
World Cup 2022
Tech Support
Computer Build, Upgrade & Buying Resource Thread
TL Community
The Automated Ban List
Blogs
A Better Routine For Progame…
TrAiDoS
StarCraft improvement
iopq
Heero Yuy & the Tax…
KrillinFromwales
I was completely wrong ab…
jameswatts
Need Your Help/Advice
Glider
Trip to the Zoo
micronesia
Customize Sidebar...

Website Feedback

Closed Threads



Active: 17964 users

Flash on DeepMind: "I think I can win" - Page 4

Forum Index > SC2 General
Post a Reply
Prev 1 2 3 4 5 6 8 9 10 Next All
Cuce
Profile Joined March 2011
Turkey1127 Posts
March 10 2016 17:30 GMT
#61
Flash hit the key point I think.

Go and chess are games of complete information, where as starcraft is a game of incomplete information. furthermore, the more information you get usually means the mroe resouce you spent on getting information.

sure, a computer can calculate possible situations with given incomplete information, but to match what we call meta game and intuition of pro players, will take a really long time of self learning ana data collecting on computers part.
64K RAM SYSTEM 38911 BASIC BYTES FREE
NinjaToss
Profile Blog Joined October 2015
Austria1383 Posts
March 10 2016 17:33 GMT
#62
I mean the problem is if Flash's wrist can keep up with him. He's playing BW "casually" and he already say that his arms hurt, to return to his former bonjwa self would be hard considering his injury.
I'm sorry for all those that got their hearts broken by Zest | Zest, Bisu, soO, herO, MC, Maru, TY, Rogue, Trap, TaeJa", Favourite foreigners: ShoWTimE, Snute, Serral and Nerchio| KT BEST KT |
Cuce
Profile Joined March 2011
Turkey1127 Posts
March 10 2016 17:36 GMT
#63
On March 11 2016 02:11 eScaper-tsunami wrote:
Show nested quote +
On March 11 2016 00:42 BisuDagger wrote:
(Z)hero can operate at about 450-500 apm on a consistent basis. To make this fair, the actions per minute should be clamped to <=600


The sad thing is it doesn't take 600 apm to have perfect micro. In the end it boils down to accuracy and efficiency.



btw does broodwar has a hardlimit for command accepted per frame?
like 12 per frame or something.

I wouldnt be suprised if there was, at least a limit to buffering
64K RAM SYSTEM 38911 BASIC BYTES FREE
Taf the Ghost
Profile Joined December 2010
United States11751 Posts
March 10 2016 17:37 GMT
#64
On March 11 2016 02:20 Clonester wrote:
Show nested quote +
On March 11 2016 02:14 Monochromatic wrote:
On March 11 2016 02:03 Goolpsy wrote:
Even with 400 apm limit, Neural network learning can easily teach it where to focus its micro most efficiently.

Game might seem like it, but Starcraft has far fewer strategies than chess.


I disagree. Starcraft may have fewer strategies then chess, but due to fog of war limiting information, the ai can only guess half the time. Furthermore, many strategies look the same and things such as drops could still catch the ai off guard. A starcraft game has many many more possibilities then a chess game.

The real problem though is that chess is turn based while starcraft is real time. This means that the computer would have much less time to think. Additionally, people make mistakes in execution in starcraft that differentiate the same strategy. Take a rally point, for instance. Depending on where it is set, there is a difference in time on when units get to different places.

Chess (and go, for that matter) are turn based, so making a move is the same for a grandmaster or a new player -- the pawn still goes to the square you want it to perfectly every time.

Finally, starcraft has so many orders of magnitude more board states then a chess board. This makes it overwhelmingly harder to try and brute force.


But thats the point. Deepthought is not like Deep Blue brute forcing its way into the game. It is making a much more soft approach by learning to play it. The neural network architecture is not ment to brute force the game and "solve it". It learns the game by millions of games against itself and replays and learns from that, takes conclusions. Deep Blue just tried out millions of next moves when playing chess. Deep Thought learned to play the game and knows what to do where.


"not like Deep Blue brute forcing its way into the game" vs "It learns the game by millions of games against itself and replays and learns from that". I don't think you quite know what "brute force" means.

I'm only poking you a little. The technology and approach are rather different between the computer systems, but they both still work by being able to call up almost the entire Game State possibility and knowing how to process through the information. This is what computers are supremely good at, but they it also shows their limitations. Though I'd be remiss if I didn't point out that most of these public games with top pro's always benefits the Computer in one very specific manner: they can analyze all of the publicly known games of the Master, allowing adaptation to the Master's play style.
L_Master
Profile Blog Joined April 2009
United States8017 Posts
March 10 2016 17:41 GMT
#65
Just the unit efficiency and micro possibilities for the AI are insane. That alone would make it insanely difficult to beat because you're guaranteed to always be outmacroed and viciously destroyed in any engagements involving similar numbers. There are videos out there of 12 goon vs 12 goon fights where the AI wins with 12 goons alive.

Some form of APM cap seems fair in my book, or else the AI isn't winning because it is making better decisions than the human, it's winning because it's exploiting micro in a way no human could ever imagine.
EffOrt and Soulkey Hwaiting!
Nakajin
Profile Blog Joined September 2014
Canada8989 Posts
March 10 2016 17:46 GMT
#66
I depend what they want to do, capping the APM would be a lot more interesting. If not of course you would win a game where you dodge every single stalker shot by hopping in and out of a medivac, in fact just doing a worker rush would probably work, but that is not realy extraordinary.
Writerhttp://i.imgur.com/9p6ufcB.jpg
boxerfred
Profile Blog Joined December 2012
Germany8360 Posts
March 10 2016 17:48 GMT
#67
there's no way a human would beat an AI in starcraft 2. take the micro bot that someone wrote here on TL as an example. SC2 has a theoretical notexistant skill gap which is beyond human reach. dunno about bw.
Savant
Profile Blog Joined October 2009
United States379 Posts
March 10 2016 17:51 GMT
#68
I think the AI can simply BBS every game and win through sheer micro
Haukinger
Profile Joined June 2012
Germany131 Posts
March 10 2016 17:56 GMT
#69
And that's why there should be a cooldown on each and every action you can do in SC2. To have a predictable behavior of the units independent of the capabilities of the player to exploit certain things. It would be so much easier and satisfying to balance, for instance, banelings if marines were unable to split.
disciple
Profile Blog Joined January 2008
9070 Posts
March 10 2016 18:09 GMT
#70
This match would have number of interesting implications chief among witch are BO decisions. If AI is strictly superior microing units theres no reason not to assume that it will try taking advantage of this and go for 1 base all-ins most of the time in order to force micro intensive early games. It would be cool if the AI has some doubt about his opponents skill and actually needs to confirm its superiority in micro in order to feel confident in winning and going for all ins. Humans already do that as we all know from Bisu being annoying as much as possible with his scouting probe. Now imagine AI controlling this, it will never die by mistake.
Administrator"I'm a big deal." - ixmike88
Grumbels
Profile Blog Joined May 2009
Netherlands7031 Posts
Last Edited: 2016-03-10 18:31:10
March 10 2016 18:27 GMT
#71
I recall some specific types of AI techniques used for mutalisk micro in one of the BWAI competitions. I wonder if the point of the deepmind project is to find applications for neuralnet type algorithms or whether they would be okay with discarding neural networks if other ai techniques would work better. I guess it is the former, since that must be the reason google funds it, so that eventually they can have self driving cars and smarter search results.

I think neural networks are used by the planetary annihilation ai designer, I used to read some of his explanations for why that was the future of rts ai, but I don't know if he is still working on similar things or where one can find information on this. iirc the ai could learn how to micro by playing against itself over and over
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.
endy
Profile Blog Joined May 2009
Switzerland8970 Posts
March 10 2016 18:28 GMT
#72
On March 10 2016 23:35 B-royal wrote:
What will be the most difficult in my opinion is to have the AI make decisions such as where to attack, when to attack, multi-pronged attacks, when to get certain units and how to use spells such as dark swarm properly. It seems to me like it would be fairly easy to trick and abuse the behavior of the AI.


I've already played a bot on BW and engagements were actually the bot's biggest strength. It's constantly scouting with zerglings, has an incredible overlord spread for a perfect map awareness which allows to always perfectly surround your army or set the best possible concave possible.

As for stuffs like swarms, how many times did your defilers die before casting the swarm because you weren't selecting/clicking fast enough?
ॐ
The_Red_Viper
Profile Blog Joined August 2013
19533 Posts
March 10 2016 18:44 GMT
#73
See the problem i have with this is that the Ai will have such a big advantage through 'mechanics' alone.
It's much more interesting in GO because there is no difference in execution, tactics and strategy is all that matters here.

Even though there are a lot more possible "board states" in sc2, i am not sure if that really matters in the end if you theoretically have a player with unlimited APM and attention.


But hey, i have obviously very little idea about it and when google says starcraft would be the next step, maybe it's harder than i think (or they really want to somewhat limit the AI in the mechanics department so it comes down to tactis/strategy, which would be weird though)
IU | Sohyang || There is no God and we are his prophets | For if ‘Thou mayest’—it is also true that ‘Thou mayest not.” | Ignorance is the parent of fear |
Goolpsy
Profile Joined November 2010
Denmark301 Posts
March 10 2016 18:50 GMT
#74
Learning by iterations and bruteforcing is not the same thing. On the same note; Chess is far from solved.

There is a continuous evolution and progression of chess engines, the best one currently being 'Komodo'.

From the Wiki: "Komodo heavily relies on evaluation rather than depth". I've been following the TCEC tournaments and heard the developers talk about certain aspects of the making of AI.

Evaluation is derived not from knowing that a certain position withs 58% of the games, but by piece value and pieceplacement + structures.

If you have a chain of pawns (x= pawn, o = empty space)

oxo or oox or oxo
xoo xxo xox

They do not have a evaluation of 3 (1 per pawn), but more than 3. In the same way, having an isolated pawn (A pawn with no friendly pawns on either adjecent diagonal), it is usually very weak and worth less than 1.

Why is this important ?
Being able to evaluate a situation through dividing out the area/map is almost directly transferable to Starcraft. It can be used for unitplacement to scout, defending chokepoints, building placement or engagement angles (without too much processing even).

As for incomplete information; it is not all that hard. you don't need to know all units produced to calculate possible strategies available or techtrees possible at a current time. I know it seems like it, but you don't have complete information in either chess or Go. (not that is it not a game of complete information, as you can't hold all possible iterations and payoff thereof in memory, )
Empirimancer
Profile Joined July 2011
Canada1024 Posts
March 10 2016 18:52 GMT
#75
For this to be an interesting challenge for DeepMind the AI would have to be limited to 400 APM and it would have to interact through a virtual keyboard and mouse, i.e. it would have to actually drag the cursor to box units, etc, so it can't do micro that is (in principle) impossible for humans to do.



ZAiNs
Profile Joined July 2010
United Kingdom6525 Posts
March 10 2016 19:01 GMT
#76
On March 11 2016 03:44 The_Red_Viper wrote:
See the problem i have with this is that the Ai will have such a big advantage through 'mechanics' alone.
It's much more interesting in GO because there is no difference in execution, tactics and strategy is all that matters here.

Even though there are a lot more possible "board states" in sc2, i am not sure if that really matters in the end if you theoretically have a player with unlimited APM and attention.


But hey, i have obviously very little idea about it and when google says starcraft would be the next step, maybe it's harder than i think (or they really want to somewhat limit the AI in the mechanics department so it comes down to tactis/strategy, which would be weird though)

How would it be weird to limit the mechanics? The goal is to be 'smarter' than a human, without limiting mechanics it wouldn't really prove anything or be an accomplishment. I imagine they would want to even limit the mechanics so that they're slightly below the absolute best players mechanically. Attention is a resource in SC2 and I think it'll be hard to give the AI imperfect mini-map awareness or imperfect mouse-accuracy without creating too complicated of a model, but things like actual keypresses a second and cursor speed will be easy to limit.
Blargh
Profile Joined September 2010
United States2101 Posts
March 10 2016 19:01 GMT
#77
I suspect there would be a variety of cheese tactics where the AI could simply out-micro the players to such an extreme degree that they can always win in the first 10 minutes.
Green_25
Profile Joined June 2013
Great Britain696 Posts
Last Edited: 2016-03-10 19:07:11
March 10 2016 19:06 GMT
#78
I'm very skeptical that this could work in an RTS like starcraft.

Even the micro I'm doubtful could be perfect. I may well be wrong however, and if I am this thing scares the shit out of me
Loccstana
Profile Blog Joined November 2012
United States833 Posts
March 10 2016 19:06 GMT
#79
This would be of interest to people interested in AI for Starcraft:

https://webdocs.cs.ualberta.ca/~cdavid/pdf/starcraft_survey.pdf

A conservative lower bound on the state space of brood war is 10^1685. This is many orders of magnitude above the state space of Go, which is 10^170. Whats more, the branching factor is 10^50 to 10^200, compared to <360 for Go.
[url]http://i.imgur.com/lw2yN.jpg[/url]
Loccstana
Profile Blog Joined November 2012
United States833 Posts
March 10 2016 19:10 GMT
#80
On March 11 2016 02:30 Cuce wrote:
Flash hit the key point I think.

Go and chess are games of complete information, where as starcraft is a game of incomplete information. furthermore, the more information you get usually means the mroe resouce you spent on getting information.

sure, a computer can calculate possible situations with given incomplete information, but to match what we call meta game and intuition of pro players, will take a really long time of self learning ana data collecting on computers part.


Starcraft is what we call a POMDP (partially observable markov decision process), there are algorithms for solving these types of problems, for example recurrent neural networks, but no one has tried applied it to something as complex as a full game in Starcraft.
[url]http://i.imgur.com/lw2yN.jpg[/url]
Prev 1 2 3 4 5 6 8 9 10 Next All
Please log in or register to reply.
Live Events Refresh
OSC
00:00
OSC Elite Rising Star #15
TBD vs ArTLIVE!
xJustxJordanx4
Liquipedia
Replay Cast
00:00
uThermal 2v2 Circuit: May
CranKy Ducklings116
Liquipedia
OSC
21:00
Mid Season Playoffs
ArT vs ReBellioN
HonMonO vs Ziomek
Shameless vs LunaSea
MilkiCow vs GgMaChine
Moja vs HiGhDrA
Jumy vs TBD
Demi vs NightPhoenix
Solar vs Cham
Liquipedia
[ Submit Event ]
Live Streams
Refresh
StarCraft 2
PiGStarcraft355
Nina 135
SteadfastSC119
Ketroc 25
EnDerr 13
NoRegreT_ 6
StarCraft: Brood War
JulyZerg 124
Icarus 9
Dota 2
monkeys_forever510
LuMiX1
Counter-Strike
Stewie2K1128
taco 482
Other Games
summit1g11351
C9.Mang01679
shahzam1238
ViBE244
ToD149
Organizations
Dota 2
PGL Dota 2 - Secondary Stream1740
StarCraft 2
Blizzard YouTube
StarCraft: Brood War
BSLTrovo
sctven
[ Show 17 non-featured ]
StarCraft 2
• Berry_CruncH281
• Hupsaiya 76
• practicex 32
• IndyKCrew
• AfreecaTV YouTube
• intothetv
• Kozan
• sooper7s
• LaughNgamezSOOP
• Migwel
StarCraft: Brood War
• RayReign 23
• STPLYoutube
• ZZZeroYoutube
• BSLYoutube
League of Legends
• Doublelift5794
• Stunt201
Other Games
• Scarra1523
Upcoming Events
WardiTV Invitational
7h 34m
HiGhDrA vs Nicoract
MaNa vs HiGhDrA
HiGhDrA vs Reynor
Nicoract vs Reynor
MaNa vs Nicoract
MaNa vs Reynor
MaxPax vs Spirit
Krystianer vs Spirit
OSC
9h 34m
BSL 2v2 ProLeague S3
15h 34m
Korean StarCraft League
23h 34m
SOOP
1d 5h
sOs vs Percival
CranKy Ducklings
1d 6h
WardiTV Invitational
1d 7h
Cheesadelphia
1d 11h
CSO Cup
1d 13h
BSL: ProLeague
1d 14h
Hawk vs UltrA
Sziky vs spx
TerrOr vs JDConan
[ Show More ]
GSL Code S
2 days
Rogue vs herO
Classic vs GuMiho
Sparkling Tuna Cup
2 days
BSL: ProLeague
2 days
Bonyth vs Dewalt
Cross vs Doodle
MadiNho vs Dragon
Replay Cast
2 days
Wardi Open
3 days
Replay Cast
3 days
Replay Cast
4 days
RSL Revival
4 days
Cure vs Percival
ByuN vs Spirit
RSL Revival
5 days
herO vs sOs
Zoun vs Clem
Replay Cast
5 days
The PondCast
6 days
RSL Revival
6 days
Serral vs SHIN
Solar vs Cham
Replay Cast
6 days
Liquipedia Results

Completed

CSL Season 17: Qualifier 2
BGE Stara Zagora 2025
Heroes 10 EU

Ongoing

JPL Season 2
BSL 2v2 Season 3
BSL Season 20
KCM Race Survival 2025 Season 2
NPSL S3
Rose Open S1
CSL 17: 2025 SUMMER
2025 GSL S2
BLAST.tv Austin Major 2025
ESL Impact League Season 7
IEM Dallas 2025
PGL Astana 2025
Asian Champions League '25
BLAST Rivals Spring 2025
MESA Nomadic Masters
CCT Season 2 Global Finals
IEM Melbourne 2025
YaLLa Compass Qatar 2025
PGL Bucharest 2025

Upcoming

Copa Latinoamericana 4
CSLPRO Last Chance 2025
CSLPRO Chat StarLAN 3
K-Championship
SEL Season 2 Championship
Esports World Cup 2025
HSC XXVII
Championship of Russia 2025
Murky Cup #2
Esports World Cup 2025
BLAST Bounty Fall 2025
BLAST Bounty Fall Qual
IEM Cologne 2025
FISSURE Playground #1
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 © 2025 TLnet. All Rights Reserved.