Re: [Computer-go] KGS mixed human-and-bot tournaments

Isn't this byoyomi heavily in favor of bots? Just asking. On 8/31/16 10:24 AM, Nick Wedd wrote: KGS has announced that it will be running, for the first time, a "mixed" tournament where both humans and bots can play on the same terms. This will be held on Saturday and Sunday, September 17th/

Re: [Computer-go] Having an "estimated winrate" on the AGA pro game broadcasts

If you want something quick could use any engine that supports the gtp command "final_score". It doesnt give win rate but will report who it thinks won and by how many points. GnuGo.. pachi or commercial engines likely all support it.. but calculation in early game can lag.. like 30s to 1min for gn

Re: [Computer-go] Having an "estimated winrate" on the AGA pro game broadcasts

Hey Andrew! Since talking about it with you over the weekend, I've been working on something pretty similar: a fishnet clone that basically installs the latest pachi (pre-configured with a pattern table, the 54% DCNN network, an opening book, etc) onto a willin

Re: [Computer-go] Having an "estimated winrate" on the AGA pro game broadcasts

One could use a curve to map the MC winning rate to an actual winning probability. It would take only thousands of games to learn such a curve (as opposed to the 30 million games used to train the value network in AlphaGo). Álvaro. On Wed, Aug 31, 2016 at 8:24 PM, Dan Schmidt wrote: > Hi Andrew

Re: [Computer-go] Having an "estimated winrate" on the AGA pro game broadcasts

Hi Andrew, I enjoy the AGA broadcasts. I am mostly just an observer on this list rather than a go programming expert, but I do have a couple of things to say on this topic: 1. This is done all the time on chess broadcasts these days, and I hate it. I want to know what a strong player thinks is goi

Re: [Computer-go] Having an "estimated winrate" on the AGA pro game broadcasts

Ah, i forgot to put the links to example broadcasts: Our recent broadcast of the Bailing cup semifinals: https://www.youtube.com/watch?v=VXCkkC341L8 A live game from the recent US Go Congress: https://www.youtube.com/watch?v=Z3lPUKSQU3g (commentary starts ~45 minutes in) BTW, i'd like to point o

Re: [Computer-go] Having an "estimated winrate" on the AGA pro game broadcasts

Estimating winrate is actually a very challenging problem.. particularly in early and midgame. AlphaGo did create a value network that could help.. but dont think any value networks are publicly available and even then cant trust till later in game. Could get guesses for next moves from a supervis

[Computer-go] Having an "estimated winrate" on the AGA pro game broadcasts

Hello all! Long time lurker, first time poster: I'm Andrew Jackson, i volunteer w/ the AGA in a number of capacities. Most recently, i've been putting together live broadcasts of games -- professional games from CJK, and also games from AGA events [1] These broadcasts feature professional comme

[Computer-go] KGS mixed human-and-bot tournaments

KGS has announced that it will be running, for the first time, a "mixed" tournament where both humans and bots can play on the same terms. This will be held on Saturday and Sunday, September 17th/18th. The tournament is in two divisions, suitable for different time zones. Both are 19x19, No Handi