Re: [Computer-go] Patterns and bad shape

2017-04-18 Thread lemonsqueeze
I think that's ok: the prediction systems are already used to deal with a huge number of positions during training, it's just a matter of changing the quality of these positions. Say instead of training on 100% good answers to good moves from games, we could take half as many and train on 50%

Re: [Computer-go] Patterns and bad shape

2017-04-18 Thread Brian Sheppard via Computer-go
...@gmail.com] Sent: Tuesday, April 18, 2017 9:06 AM To: computer-go@computer-go.org; Brian Sheppard <sheppar...@aol.com> Subject: Re: [Computer-go] Patterns and bad shape Now, I love this idea. A super fast cheap pattern matcher can act as input into a neural network input layer in sort of

Re: [Computer-go] Patterns and bad shape

2017-04-18 Thread Gian-Carlo Pascutto
On 17-04-17 15:04, David Wu wrote: > If you want an example of this actually mattering, here's example where > Leela makes a big mistake in a game that I think is due to this kind of > issue. Ladders have specific treatment in the engine (which also has both known limitations and actual bugs in

Re: [Computer-go] Patterns and bad shape

2017-04-18 Thread Jim O'Flaherty
omputer-go.org] *On Behalf Of *Jim O'Flaherty *Sent:* Monday, April 17, 2017 7:05 AM *To:* computer-go@computer-go.org *Subject:* Re: [Computer-go] Patterns and bad shape It seems chasing down good moves for bad shapes would be an explosion of "exception cases", like combinatorially huge

Re: [Computer-go] Patterns and bad shape

2017-04-18 Thread Brian Sheppard via Computer-go
-boun...@computer-go.org] On Behalf Of Jim O'Flaherty Sent: Monday, April 17, 2017 7:05 AM To: computer-go@computer-go.org Subject: Re: [Computer-go] Patterns and bad shape It seems chasing down good moves for bad shapes would be an explosion of "exception cases", like combinatoriall

Re: [Computer-go] Patterns and bad shape

2017-04-17 Thread Jonathan Roy
David Wu wrote: > Black (X) to move. The screenshot showed that Leela's policy net put about > 96% probability on a and only 1.03% on b. And that even after nearly 1 > million simulations had basically not searched b at all. Leela does read out ladders to the end, it doesn't rely on policy

Re: [Computer-go] Patterns and bad shape

2017-04-17 Thread David Wu
Hmm. Do you know that Leela does something special here? When I look at Leela's analysis output it seems to the search seems not to consider the ladder escape because the policy net assigns a low probability to it (and such a high probability to move in the upper right). Which is the same as in

Re: [Computer-go] Patterns and bad shape

2017-04-17 Thread Stefan Kaitschick
On Mon, Apr 17, 2017 at 3:04 PM, David Wu wrote: > To some degree this maybe means Leela is insufficiently explorative in > cases like this, but still, why does the policy net not put H5 more than > 1.03%. After all, it's vastly more likely than 1% that that a good player

Re: [Computer-go] Patterns and bad shape

2017-04-17 Thread David Wu
Hmmm, screenshot doesn't seem to be getting through to the list, so here's a textual graphic instead. A B C D E F G H J K L M N O P Q R S T +---+ 19 | . . . . . . . . . . . . . . . . . . . | 18 | . . . . . . . . . . . . . . . . . . . | 17 | .

Re: [Computer-go] Patterns and bad shape

2017-04-17 Thread Jim O'Flaherty
It seems chasing down good moves for bad shapes would be an explosion of "exception cases", like combinatorially huge. So, while you would be saving some branching in the search space, you would be ballooning up the number of patterns for which to scan by orders of magnitude. Wouldn't it be

[Computer-go] Patterns and bad shape

2017-04-17 Thread lemonsqueeze
Hi, I'm sure the topic must have come up before but i can't seem to find it right now, i'd appreciate if someone can point me in the right direction. I'm looking into MM, LFR and similar cpu-based pattern approaches for generating priors, and was wondering about basic bad shape: Let's say we