Re: [Computer-go] Some personal thoughts on 9x9 computer go

That was very interesting, thanks for sharing! On Fri, Mar 2, 2018 at 9:50 AM, wrote: > Hi, > somebody asked me to post my views on 9x9 go on the list based on my > experience with correspondence go on OGS and little Golem. > > I have been playing online correspondence

Re: [Computer-go] 9x9 is last frontier?

Hello Aja, Could you enlighten me on how AlphaZero handles tactics in chess ? It seems the mcts approach as described in the paper does not perform well enough. Leela-chess is not performing well enough even though leela-go seems to be doing well. Daniel On Fri, Mar 2, 2018 at 4:52 AM,

[Computer-go] IEEE CIG 2018: Full Papers due March 15

CALL FOR PAPERS: 2018 IEEE Conference on Computational Intelligence and Games Maastricht University - Department of Data Science & Knowledge Engineering, Maastricht, The Netherlands, August 14-17, 2018

[Computer-go] Some personal thoughts on 9x9 computer go

Hi, somebody asked me to post my views on 9x9 go on the list based on my experience with correspondence go on OGS and little Golem. I have been playing online correspondence tournaments since 2011 with Valkyria which is a MCTS heavy playout MCTS using AMAF heavily tuned for 9x9. Also with

Re: [Computer-go] 9x9 is last frontier?

Do you think deep learning can understand and solve double ko, for example? Hideki Aja Huang:

Re: [Computer-go] Out of couriosity ...

More curiosity: what about non square boards? Are go programs a cheap way to explore go in such boards? :D Fidel Santiago. On 02 Mar 2018 12:09, Ingo Althöfer <3-hirn-ver...@gmx.de> wrote: > Hello, > > looking at boards of different sizes, may there > be some threshold d, such that the Zero

Re: [Computer-go] 9x9 is last frontier?

Where is leela chess. How many games it is trained on? Le 2 mars 2018 18:20, "Dan" a écrit : > Hello Aja, > > Could you enlighten me on how AlphaZero handles tactics in chess ? > > It seems the mcts approach as described in the paper does not perform well > enough. > >

[Computer-go] Some personal thoughts on 9x9 computer go

HI, I was informed on the thread of the topic 9x9 go as Mangus had stated some good points that were similar to mine. Mine are based on my experience of correspondence go on OGS and GoQuest. I have been playing online go 2011 with Deep Scholar which originally was Fuego with large GoQuest

Re: [Computer-go] 9x9 is last frontier?

Leela chess is here https://github.com/glinscott/leela-chess It uses the exact MCTS algorithm as described in AlphaZero, with value and policy networks, but performs really badly in tactics (often missing 2-3 ply shallow tactics) To get a somewhat strong MCTS chess engine, I had to use

[Computer-go] Out of couriosity ...

Hello, looking at boards of different sizes, may there be some threshold d, such that the Zero approach is in particular successfull for all boards larger than dxd und less successfull for boards smaller than dxd? Or does duccess increase gradually with board size? Second question: Go may also

Re: [Computer-go] 9x9 is last frontier?

2018-03-02 6:50 GMT+00:00 "Ingo Althöfer" <3-hirn-ver...@gmx.de>: > Von: "David Doshay" > > Go is hard. > > Programming is hard. > > > > Programming Go is hard squared. > > ;^) > > And that on square boards. > Mama mia! > Go is hard for humans, but in my own opinion I think Go