Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-22 Thread John Tromp
>> (Japanese rules are not *that* hard. IIRC, Many Faces, and all other >> programs, including my own, scored in them > > There is a huge difference between doing some variation of territory > scoring and implementing Japanese rules. Understanding this difference > will get you some way to

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-22 Thread Gian-Carlo Pascutto
On 22-03-17 16:27, Darren Cook wrote: > (Japanese rules are not *that* hard. IIRC, Many Faces, and all other > programs, including my own, scored in them There is a huge difference between doing some variation of territory scoring and implementing Japanese rules. Understanding this difference

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-22 Thread Darren Cook
>>> The issue with Japanese rules is easily solved by refusing to play >>> under ridiculous rules. Yes, I do have strong opinions. :) >> >> And the problem with driver-less cars is easily "solved" by banning >> all road users that are not also driver-less cars (including all >> pedestrians, bikes

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-22 Thread Álvaro Begué
Thank you, Gian-Carlo. I couldn't have said it better. Álvaro. On Wed, Mar 22, 2017 at 7:07 AM, Gian-Carlo Pascutto wrote: > On 22-03-17 09:41, Darren Cook wrote: > >> The issue with Japanese rules is easily solved by refusing to play > >> under ridiculous rules. Yes, I do

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-22 Thread Gian-Carlo Pascutto
On 22-03-17 09:41, Darren Cook wrote: >> The issue with Japanese rules is easily solved by refusing to play >> under ridiculous rules. Yes, I do have strong opinions. :) > > And the problem with driver-less cars is easily "solved" by banning > all road users that are not also driver-less cars

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-22 Thread Darren Cook
> The issue with Japanese rules is easily solved by refusing to play under > ridiculous rules. Yes, I do have strong opinions. :) And the problem with driver-less cars is easily "solved" by banning all road users that are not also driver-less cars (including all pedestrians, bikes and wild

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-22 Thread Gian-Carlo Pascutto
On 22-03-17 00:36, cazen...@ai.univ-paris8.fr wrote: > > Why can't you reuse the same self played games but score them If you have self-play games that are played to the final position so scoring is fool-proof, then it could work. But I think things get really interesting when timing of a pass

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-22 Thread Detlef Schmicker
oakfoam value network does exactly this, we have 6 komi layers -7.5 -5.5 -0.5 0.5 5.5 7.5 (+ and - due to color played) and trained from 4d+ kgs games with this: if (c_played==1): if ("0.5" in komi): komiplane=1; if ("6.5" in komi or "2.75" in komi or "5.5" in komi): #komi 6.5

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-21 Thread Álvaro Begué
I was thinking the same thing. You can easily equip the value network with several outputs, corresponding to several settings of komi, then train as usual. The issue with Japanese rules is easily solved by refusing to play under ridiculous rules. Yes, I do have strong opinions. :) Álvaro. On

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-21 Thread uurtamo .
I guess that 1 point in such a game matters to the evaluation function. Pretty fascinating. Can you not train for the two different rulesets and just pick which at the beginning? Ignoring Chinese versus Japanese, just training on komi? Or is the problem of Japanese rules the whole issue? (I.e not

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-21 Thread Chun Sun
How does Zen know it's playing a Japanese rule game? Can it be set to play a Chinese rule game and hope to converge at the end? On Mar 21, 2017 8:03 AM, "Hideki Kato" wrote: > The value network has been trained with Chinese rules and 7.5 > pts komi. Using this for

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-21 Thread cazenave
Why can't you reuse the same self played games but score them with a different komi value ? The policy network does not use the komi to choose its moves so it should make no difference. > On 21/03/2017 21:08, David Ongaro wrote: >>> But how would you fix it? Isn't that you'd need to retrain

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-21 Thread Gian-Carlo Pascutto
On 21/03/2017 21:08, David Ongaro wrote: >> But how would you fix it? Isn't that you'd need to retrain your value >> network from the scratch? > > I would think so as well. But I some months ago I already made a > proposal in this list to mitigate that problem: instead of training a > different

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-21 Thread Paweł Morawiecki
Hideki, Using this for Japanese and 6.5, there will be some >> error in close games. We knew this issue and thought such >> chances would be so small that postponed correcting (not so >> easy). >> > But how would you fix it? Isn't that you'd need to retrain your value network from the scratch?

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-21 Thread Aja Huang via Computer-go
On Tue, Mar 21, 2017 at 10:48 AM, Hideki Kato wrote: > The value network has been trained with Chinese rules and 7.5 > pts komi. Using this for Japanese and 6.5, there will be some > error in close games. We knew this issue and thought such > chances would be so small

Re: [Computer-go] Zen lost to Mi Yu Ting

2017-03-21 Thread Hideki Kato
The value network has been trained with Chinese rules and 7.5 pts komi. Using this for Japanese and 6.5, there will be some error in close games. We knew this issue and thought such chances would be so small that postponed correcting (not so easy). Best, Hideki Pawe Morawiecki: