• Log InLog In
  • Register
Liquid`
Team Liquid Liquipedia
EST 02:38
CET 08:38
KST 16:38
  • 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
Team Liquid Map Contest #2312[ASL22] Finals Preview: Sweet Victory!12[ASL22] Ro4 Preview: Mirror Mirror6[ASL22] Ro8 Preview: Within Reach5[ASL22] Ro8 Preview: In A Tizzy11
Community News
Weekly Cups (Nov 9-15): Clem and herO take over6Dark completes military service, returns to SC217[BSL23] RO16 Group Stage20Weekly Cups (Nov 2-8): herO back on top?2Weekly Cups (Oct 26 - Nov 1): MaxPax, herO, Solar win0
StarCraft 2
General
Weekly Cups (Nov 9-15): Clem and herO take over SC4ALL: II Indiegogo Campaign Announcement No more SC2 streamers on team liquid? Team Liquid Map Contest #23 StarCraft open world shooter announced at BlizzCon
Tourneys
RSL goes to London! 2026 Offline Finals Nov 21-22 soO & FanTaSy return! SC2 Kevin Scrim 4v4 (Nov 16) Sparkling Tuna Cup - Weekly Open Tournament Sea Duckling Open (Global, Bronze-Diamond) Dark returns! GSL CK #7 4v4 Team Battle (Nov 19)
Strategy
[H] ZvP Mid-Late Game: Stalkers Collossi HT
Custom Maps
[G] How to playtest arcade maps Starcraft 2 Advance [D] the control group Simple Questions/Answers
External Content
Mutation # 552 Secret Storm The PondCast: SC2 News & Results Mutation # 551 Robotic Revival Mutation # 550 Graveyard Shift
Brood War
General
Potentially helpful Shield Battery feedback. People still play BW? SC4ALL: II Indiegogo Campaign Announcement List of top players active on ShieldBattery XUN appreciation thread
Tourneys
2v2v2v2 Tournament Stage 2: Players [BSL23] Ro16 Group B - Saturday 21:00 CET KCM Race Survival 2026 Season 4 SC1 Kevin Scrim hosted by SOOP (Nov 18-19)
Strategy
Pluto's TvP 5Marine 2Medic Push Simple Questions, Simple Answers Infested Terran strategies in 2026 Nuke strategy worked in K-League 2026-11-09
Other Games
General Games
Nintendo Switch Thread The PlayStation 5 Stormgate/Frost Giant Megathread Warcraft III: The Frozen Throne Free Space RTS Game, optimised f. Phone/Tablet etc
Dota 2
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 The Games Industry And ATVI Russo-Ukrainian War Thread Trading/Investing Thread
Fan Clubs
Fan Club Resource Thread Reynor Fan Club The Flash Fan Club
Media & Entertainment
Movie Discussion! Anime Discussion Thread [Manga] One Piece
Sports
Football (Soccer) Thread TeamLiquid Health and Fitness Initiative For 2023
World Cup 2022
Tech Support
Computer Build, Upgrade & Buying Resource Thread
TL Community
The Automated Ban List Recent Gifted Posts
Blogs
The time I organised my…
AssyrianKing
Why I built Repalyzer (1.1.…
BlueStar
Innovate or Game Over?
TrAiDoS
ShieldBattery on Mac
Kraekkling
Can Bots Beat Pros?? Starcr…
namkraft
James Bond movies ranking - pa…
Topin
StarCraft improvement
iopq
Customize Sidebar...

Website Feedback

Closed Threads



Active: 18502 users

Go - AlphaGo (Google) vs Lee Sedol (world champ)

Forum Index > General Games
Post a Reply
1 2 3 4 5 6 7 8 Next All
BlueRoyaL
Profile Blog Joined February 2006
United States2493 Posts
March 09 2016 17:06 GMT
#1
Hey guys,

I'm not sure how many of you are aware of the old Chinese game "Go", and of the current Bo5 match going on between Google's deep learning AI machine AlphaGo versus the world's champion, Lee Sedol hailing from South Korea.

Late last year, AlphaGo was able to knock off Europe's champion 5 to nil. So what's the big deal this time around?

Simply put, the level of competition (against AlphaGo). Europe's champion, Fan Hui, is a level 2-dan player. Lee Sedol is 9-dan. The statistical probability of a 9-dan player beating a 2-dan player is over 95%.

Last night, the first game was played, with AlphaGo taking the early lead 1-0. This marks an amazing point of progress for AI, and more specifically, deep learning capabilities. The reason AI hasn't been able to handily beat professional Go players until very recently is simply because of the complexity of the game. The possible permutations in Go, exceeds that of the number of atoms in the universe (and for marked effect, by several orders of magnitude at that!). If you're a visual person, Go has about 1,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000 possible permutations. So it's pretty clear, that computers don't have the capability to win these games through brute-force computations. There simply doesn't exist the computational power to do so, especially considering that these matches are played with an allotted total time for each player, similar to how professional Chess matches are played.

Google's AlphaGo has gotten to this point by deep learning. It's able to view recordings of professional matches and learn. It can also not only learn from the mistakes and moves of its' own games played, but it also has the huge advantage that it can play against itself at speeds incomprehensible for us simple humans

Anyways, I thought some of you might find it interesting. I don't play Go much myself, and I don't have the time to watch the live streams of the matches. But I think it's fascinating because at some point, there may not exist a game out there that some form of AI can't beat us at.

Here's a few extras (including live stream link for those of you interested):

1st match recording:
www.youtube.com

List of live recordings and their schedules:
www.youtube.com

An awesome Wired article, detailing the history of Go and why (at that time, 2014) computers still can't beat humans:
www.wired.com

An ArsTechnica article about this current matchup:
arstechnica.com

And an awesome and relevant xkcd image (although it now needs updating!):
[image loading]

Hope this has stirred up some interested. These are amazing times we live in!
WHAT'S HAPPENIN
Powerpill
Profile Blog Joined October 2002
United States1693 Posts
March 09 2016 17:42 GMT
#2
SKynet begins with go? Seriously though, I was impressed with deep blue all those years ago and am equally impressed now (Go I think would be much harder to program than a chess AI, as you said with the near infinite possible permutations).
The pretty things are going to hell, they wore it out but they wore it well
RoyGBiv_13
Profile Blog Joined August 2010
United States1275 Posts
Last Edited: 2016-03-09 19:27:21
March 09 2016 19:26 GMT
#3
The algorithm that AlphaGo used is a Monte Carlo tree search algorithm. In this algorithm, you start with a couple guesses as to reasonable plays based on heuristics, then evaluate each of those guesses by picking random counter moves for each potential move and seeing what can work and what can't. What AlphaGo has improved upon since this algorithm first came into Go in 2006 is two neural networks, and the training techniques for each one:
1) A network for predicting good potential moves in a present situation
2) A network for evaluating a board position

These neural networks make the tree search algorithm much more effective by eliminating obviously bad moves from the search and allowing the algorithm to evaluate board positions without having to simulate more future plays.

Also:
Any sufficiently advanced technology is indistinguishable from magic
ne4aJIb
Profile Blog Joined July 2011
Russian Federation3209 Posts
March 09 2016 19:47 GMT
#4
I guess they mean Brood War
Bisu,Best,Stork,Jangbi and Flash, Fantasy, Leta, Light and Jaedong, Hydra, Zero, Soulkey assemble in ACE now!
TheEmulator
Profile Blog Joined July 2010
28104 Posts
March 09 2016 19:48 GMT
#5
I watched a bit of the first match and will hopefully catch more of the next one. I have a feeling Lee Sedol is gonna get 5-0'd though.
Administrator
nepeta
Profile Blog Joined May 2008
1872 Posts
March 09 2016 19:58 GMT
#6
Idk about calvinball, but after the latest broodwar AI conference, broodwar got estimated to take another 5-20 years to be 'humanly solved'. We've sent them an invitation though, just in case their brute force methods won't work for broodwar.
Broodwar AI :) http://sscaitournament.com http://www.starcraftai.com/wiki/Main_Page
Oshuy
Profile Joined September 2011
Netherlands529 Posts
March 09 2016 20:10 GMT
#7
On March 10 2016 04:26 RoyGBiv_13 wrote:
The algorithm that AlphaGo used is a Monte Carlo tree search algorithm. In this algorithm, you start with a couple guesses as to reasonable plays based on heuristics, then evaluate each of those guesses by picking random counter moves for each potential move and seeing what can work and what can't. What AlphaGo has improved upon since this algorithm first came into Go in 2006 is two neural networks, and the training techniques for each one:
1) A network for predicting good potential moves in a present situation
2) A network for evaluating a board position

These neural networks make the tree search algorithm much more effective by eliminating obviously bad moves from the search and allowing the algorithm to evaluate board positions without having to simulate more future plays.

Also: https://twitter.com/deeplearning4j/status/706541229543071745


The learning of the various networks is a fun part. First supervised learning to get a network that predicts correctly the next "human" move on a set of games (they let it train on a games database until it got ~60% of the time the human move), then get several copies of the network to play against itself in reinforcement learning on the whole game (when the game is won, the network changes for that game are valued more). The best network after ... lots of games was elected to predict the potential moves.

The second network is then used on the complete set, trained until it accurately provides an outcome (color winning) from a given position.

Combine the two with a standard Monte Carlo and you get a very good engine.

The only surprising part for me is how well the convergence on the two networks seems to have worked. In my days the networks tended to spend a few days learning to end up with barely better results than randomness (except on a select few problems). Then again, we worked with 3 layers and 50 neurones total (not including the programmer's).
Coooot
{CC}StealthBlue
Profile Blog Joined January 2003
United States41117 Posts
Last Edited: 2016-03-09 20:12:34
March 09 2016 20:11 GMT
#8
I would imagine the real development will be when AlphaGo knows the Human has lost before the player has made his/her move or counter.
"Smokey, this is not 'Nam, this is bowling. There are rules."
Manit0u
Profile Blog Joined August 2004
Poland17875 Posts
March 09 2016 20:16 GMT
#9
Snakes & Ladders - lol. I guess you can put Monopoly in there too...
Time is precious. Waste it wisely.
DarkPlasmaBall
Profile Blog Joined March 2010
United States46753 Posts
March 09 2016 21:30 GMT
#10
Yeah there are a few TL threads about Go

Like this one: http://www.teamliquid.net/forum/games/89504-tl-go-group?page=9#165
"There is nothing more satisfying than looking at a crowd of people and helping them get what I love." ~Day[9] Daily #100
mahrgell
Profile Blog Joined December 2009
Germany3943 Posts
March 09 2016 21:49 GMT
#11
Or: http://www.teamliquid.net/forum/games/129753-go-igo-weiqi-baduk which is even on the first page of this subforum... (for obvious reasons)
Yurie
Profile Blog Joined August 2010
12200 Posts
March 09 2016 21:51 GMT
#12
Sad the first game recording is so low quality, audio choppy and cuts to the wrong camera all the time.
mahrgell
Profile Blog Joined December 2009
Germany3943 Posts
March 09 2016 22:15 GMT
#13
For those looking for a (English) video live analysis of the game adressed to a more Go educated crowd:

The same channel will broadcast as well in the future. But as I said, you should have a decent understanding of Go to be able to follow that broadcast, while the regular stream is more adressed at beginners.
For those just looking for a quick summary and analysis of the game in written form, you can look here:
https://gogameguru.com/alphago-defeats-lee-sedol-game-1/
It should be noted, that this summary is done by another 9p, but is actually summarizing a lot of different korean media/professional opinions on the match.
datscilly
Profile Blog Joined November 2007
United States529 Posts
March 09 2016 22:16 GMT
#14
On March 10 2016 06:51 Yurie wrote:
Sad the first game recording is so low quality, audio choppy and cuts to the wrong camera all the time.


Check out American Go Association's stream vod: https://www.youtube.com/watch?v=6ZugVil2v4w
It starts an hour into the match, commentary is quicker and less oriented towards beginners.

Interesting thing about that xkcd comic: in Arimaa a bot beat the best human players just last year (in April). So the field of AI in games appears to be advancing rapidly.

I'm personally excited by the possibility of AI becoming superhumanly good at other tasks, as well as games. Like how driverless cars + Show Spoiler +
I hope the term auto catches on
will be better than humans, but for medicine, or scientific research.
SoSexy
Profile Blog Joined February 2011
Italy3725 Posts
March 10 2016 08:27 GMT
#15
The robot won again o.o 2-0
Dating thread on TL LUL
TheEmulator
Profile Blog Joined July 2010
28104 Posts
March 10 2016 08:28 GMT
#16
AlphaGo owns. We're doomed.
Administrator
purakushi
Profile Joined August 2012
United States3312 Posts
March 10 2016 08:30 GMT
#17
LLWWW...

Sigh, but no really. Humanity lost. Probably 0-5.
T P Z sagi
SChlafmann
Profile Joined September 2011
France725 Posts
March 10 2016 10:34 GMT
#18
Close match still if I understood correctly. Some poor quality news website says that Lee lost from only 2 points after a 5h game. Crazy shit. I believe that if Lee doesn't win next one it will be a clean sweep 5-0.
Otherwise 4-1, but I don't see him defeating the AI twice.
Damn.
"More GG, more skill" - Nope! Chuck Testa - #BISU2013
ETisME
Profile Blog Joined April 2011
12912 Posts
March 10 2016 11:02 GMT
#19
could there exist a person who excel in beating computer go since as some said, go is a less logic game compared to chess
其疾如风,其徐如林,侵掠如火,不动如山,难知如阴,动如雷震。
Grumbels
Profile Blog Joined May 2009
Netherlands7032 Posts
March 10 2016 13:04 GMT
#20
I wonder if they're going to continue developing AlphaGo. Maybe it was only a proof of concept type product? For instance, chess engines are not that interesting any more for research programs. I kinda hope they won't, I felt like chess was more mysterious before computers.
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.
1 2 3 4 5 6 7 8 Next All
Please log in or register to reply.
Live Events Refresh
The PiG Daily
06:25
Best Games of SC
Clem vs Classic
Rogue vs Neeb
MaxPax vs Bunny
SHIN vs Clem
GuMiho vs SHIN
LiquipediaDiscussion
[ Submit Event ]
Live Streams
Refresh
StarCraft: Brood War
Zeus 251
PianO 66
yabsab 10
Sacsri 7
Super Smash Bros
Mew2King42
Other Games
summit1g9520
WinterStarcraft779
JimRising 446
Fuzer 22
Organizations
Other Games
gamesdonequick782
StarCraft: Brood War
UltimateBattle 70
[ Show 10 non-featured ]
StarCraft 2
• AfreecaTV YouTube
• intothetv
• Kozan
• IndyKCrew
• Migwel
StarCraft: Brood War
• BSLYoutube
• STPLYoutube
• ZZZeroYoutube
Dota 2
• lizZardDota2334
League of Legends
• Stunt406
Upcoming Events
RSL Revival
5h 22m
Clem vs Serral
herO vs Rogue
OSC
5h 22m
IPSL
9h 22m
Ret vs ggnore13
nOmaD vs Aether
BSL
12h 22m
Bonyth vs Doodle
Kyrie vs Jimin
Replay Cast
15h 22m
WardiTV Weekly
1d 4h
Kung Fu Cup
2 days
Solar vs Classic
ByuN vs SHIN
PiGosaur Cup
2 days
The PondCast
4 days
KCM Race Survival
4 days
Liquipedia Results

Completed

Proleague 2026-11-17
Blizzard Classic Cup 2026
HCC Season 3

Ongoing

Acropolis #5
KCM Race Survival 2026 Season 4
International ShieldBattery League
BSL Season 23
IPSL Winter 2026-27
RSL Offline Finals
Calamity Cup Div. A Season 8
Underdog Cup 2026 Div 2-3
Stake Ranked Episode 6
BLAST Rivals Fall 2026
IEM Beijing 2026
PGL Masters Bucharest 2026
Stake Ranked Episode 5
1win Private Club #2
Thunderpick World Champ. '26
ESL Pro League Season 24
Stake Ranked Episode 4
1win Private Club #1
Logitech G Play Connect 2026
SL StarSeries Fall 2026
FISSURE Playground #3

Upcoming

CSL Season 23: Qualifier 1
Sector 591
YSL S4
SC4ALL II: Brood War
CSL 2026 Winter (S23) - 3v3
CSL 2026 Winter (S23)
NBSL 2026 Xiamen LAN
HSC XXX
Stellar Fest 2: Lunar Cup
StarCraft2 Weekly Open Tournament 2026 Grand Finals
SC4ALL II: StarCraft II
Kung Fu Cup 2026 Grand Finals
IEM Kraków 2027
PGL Bucharest 2027
BLAST Bounty Winter 2027
PGL Major Singapore 2026
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.