Re: [Computer-go] Training the value network (a possibly more efficient approach)
I was writing code along those lines when AlphaGo debuted. When it became clear that AlphaGo had succeeded, then I ceased work. So I don’t know whether this strategy will succeed, but the theoretical merits were good enough to encourage me. Best of luck, Brian From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of Bo Peng Sent: Tuesday, January 10, 2017 5:25 PM To: computer-go@computer-go.org Subject: [Computer-go] Training the value network (a possibly more efficient approach) Hi everyone. It occurs to me there might be a more efficient method to train the value network directly (without using the policy network). You are welcome to check my method: http://withablink.com/GoValueFunction.pdf Let me know if there is any silly mistakes :) ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] Training the value network (a possibly more efficient approach)
hi Bo, > Let me know if there is any silly mistakes :) You say "the perfect policy network can be derived from the perfect value network (the best next move is the move that maximises the value for the player, if the value function is perfect), but not vice versa.", but a perfect policy for both players can be used to generate a perfect playout which yields the perfect value... regards, -John ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
[Computer-go] Training the value network (a possibly more efficient approach)
Hi everyone. It occurs to me there might be a more efficient method to train the value network directly (without using the policy network). You are welcome to check my method: http://withablink.com/GoValueFunction.pdf Let me know if there is any silly mistakes :) ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] Golois5 is KGS 4d
Very interesting, but lets wait some days for getting an idea of the strength, 4d it reached due to games against AyaBotD3, now it is 3d again... Detlef Am 10.01.2017 um 15:29 schrieb Gian-Carlo Pascutto: > On 10-01-17 15:05, Hiroshi Yamashita wrote: >> Hi, >> >> Golois5 is KGS 4d. >> I think it is a first bot that gets 4d by using DCNN without search. > > I found this paper: > > https://openreview.net/pdf?id=Bk67W4Yxl > > They are using residual layers in the DCNN. > ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] Golois5 is KGS 4d
On 10-01-17 15:05, Hiroshi Yamashita wrote: > Hi, > > Golois5 is KGS 4d. > I think it is a first bot that gets 4d by using DCNN without search. I found this paper: https://openreview.net/pdf?id=Bk67W4Yxl They are using residual layers in the DCNN. -- GCP ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
[Computer-go] Golois5 is KGS 4d
Hi, Golois5 is KGS 4d. I think it is a first bot that gets 4d by using DCNN without search. Golois5 (4d) info says "I use a policy network trained on Gogod games." Golois4 (3d) info says "I use a policy network trained on KGS games played by 6 dan or more." If both network are same, GoGoD games is better than KGS games for DCNN? Thanks, Hiroshi Yamashita ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go