[Computer-go] Crazy Stone is back
hideki_katoh at ybb.ne.jp
Mon Mar 5 12:12:43 PST 2018
DCNNs are not magic but just non-linear continuous function
approximators with finite freedom and we can provide up to
10^8 samples (board positions) in practice.
Why do most people believe VN can approximate (perfect or
near perfect) value function? What do they estimate the
complexity of the value function for 19x19 Go?
valkyria at phmp.se: <aa3cca138c40cbd620700cc36e950aed at phmp.se>:
>My guess is that there is some kind of threshold depending on the
>relative strength of MC eval and the value function of the NN.
>If the value function is stronger than MC eval I would guess MCEval
>turns into a bad noisy feature with little benefit.
>Depending on how strong MC eval is this threshold is probably very
>different between engines. Also i can imagine that NN value function can
>have some gaping holes in its knowledge that even simple MC eval can
>patch up. Probably true for supervised learning where training data
>probably has a lot of holes since bad moves are not in the data.
>The Zero approach is different because it should converge to perfection
>in the limit, thus overcome any weaknesses of the value function early
>on. At least in theory.
>On 2018-03-05 14:04, Gian-Carlo Pascutto wrote:
>> On 5/03/2018 12:28, valkyria at phmp.se wrote:
>>> Remi twittered more details here (see the discussion with gghideki:
>> Thank you. So Remi gave up on rollouts as well. Interesting "difference
>> of opinion" there with Zen.
>> Last time I tested this in regular Leela, playouts were beneficial, but
>> this was before combined value+policy nets and much more training data
>> was available. I do not know what the current status would be.
>Computer-go mailing list
>Computer-go at computer-go.org
Hideki Kato <mailto:hideki_katoh at ybb.ne.jp>
More information about the Computer-go