[Computer-go] Value network that doesn't want to learn.

2017-06-19 Thread Vincent Richard
Hello everyone, For my master thesis, I have built an AI that has a strategical approach to the game. It doesn’t play but simply describe the strategy behind all possible move for a given strategy ("enclosing this group", "making life for this group", "saving these stones", etc). My main idea

Re: [Computer-go] Value network that doesn't want to learn.

2017-06-19 Thread Gian-Carlo Pascutto
On 19-06-17 17:38, Vincent Richard wrote: > During my research, I’ve trained a lot of different networks, first on > 9x9 then on 19x19, and as far as I remember all the nets I’ve worked > with learned quickly (especially during the first batches), except the > value net which has always been

Re: [Computer-go] Value network that doesn't want to learn.

2017-06-19 Thread Vincent Richard
This is what have been thinking about, yet unable to find an error. Currently, I'm working with: - SGF Database: fuseki info Tygem -> http://tygem.fuseki.info/index.php (until recently I was working with games of all level from KGS) - The data is then analyzed by a script which extracts all

[Computer-go] July KGS bot tournament

2017-06-19 Thread Nick Wedd
The July KGS bot tournament will be on Sunday, July 7th, starting at 08:00 UTC and end by 15:00 UTC. It will use 19x19 boards, with time limits of 14 minutes each and very fast Canadian overtime, and komi of 7½. It will be a Swiss tournament. See http://www.gokgs.com/tournInfo.jsp?id=1116 The