[Computer-go] Zero is weaker than Master!?
hideki_katoh at ybb.ne.jp
Thu Oct 26 07:17:09 PDT 2017
Xavier Combelle: <62b977d7-d227-a74d-04b7-0d46db6a727c at gmail.com>:
>It is just wild guesses based on reasonable arguments but without
Yes, of course. Due to not enough info provided by Google.
à 07:51, Hideki Kato a écrit :
>> You can believe
Of what I understand same network architecture imply the
same number of
but David Silver told AlphaGo Master used 40 layers in
>> # The paper was submitted in April.
>> Usually, network "architecture" does not imply the num
>> layers whereas "configulation" may do.
>> Clearly they made 40 layers version first because it's
>> called "1st instance" where the 80 layers one is called
>> instance." The 1st was trained 3 days and overtoo
>> Lee. Then they changed to the 2nd. Awaring t
his fact, and
>> watching the growing curve of the 1st, I g
uess 40 layers was
>> not enough to reach AlphaGo Master le
vel and so they
>> doubled the layers.
>> Xavier Combelle: <1550c907-8b96-e4ea-1f5e-2344f394b967
>>> As I understand the paper they directly cre
ated alphago zero with a 40
>>> They just made a reduced 20 block setup to co
mpare on kifu prediction
>>> (as far as I searched in the pa
per, it is the only
>>> place where they mention the 20 bloc
>>> They specifically mention comparing several ver
sion of their software.
>>> with various parameter
>>> If the number of block was an important parameter I hope they would
>>> mention it.
>>> Of course they are a lot of things that they try and failed and we will
>>> not know about
>>> But I have hard time to believe that alphago zero with a 20 block is one
>>> of them
>>> About the paper, there is no mention of the number of block of master:
>>> "AlphaGo Master is the program that defeated top human players by 600
>>> in January, 2017 34 .
>>> It was previously unpublished but uses the same neural network
>>> architecture, reinforcement
>>> learning algorithm, and MCTS algorithm as described in this paper.
>>> However, it uses the
>>> same handcrafted features and rollouts as AlphaGo Lee
>>> and training was initialised by
>>> supervised learning from human data."
>>> Of what I understand same network architecture imply the same number of
>>> Le 25/10/2017 à 17:58, Xavier Combelle a écrit :
>>>> I understand better
>>>> Le 25/10/2017 à 04:28, Hideki Kato a écrit :
>>>>> Are you thinking the 1st instance could reach Master level
>>>>> if giving more training days?
>>>>> I don't think so. The performance would be stopping
>>>>> improving at 3 days. If not, why they built the 2nd
>>>>> Xavier Combelle: <05c04de1-59c4-8fcd-2dd1-094faabf38a7 at gmail.com>:
>>>>>> How is it a fair comparison if there is only 3 days of training for
>>> Zero ?
>>>>>> Master had longer training no ? Moreover, Zero has bootstrap problem
>>>>>> because at the opposite of Master it don't learn from expert games
>>>>>> which means that it is likely to be weaker with little training.
>>>>>> Le 24/10/2017 à 20:20, Hideki Kato a écrit :
>>>>>>> David Silver told Master used 40 layers network in May.
>>>>>>> According to new paper, Master used the same architecture
>>>>>>> as Zero. So, Master used 20 blocks ResNet.
>>>>>>> The first instance of Zero, 20 blocks ResNet version, is
>>>>>>> weaker than Master (after 3 days training). So, with the
>>>>>>> same layers (a fair comparison) Zero is weaker than
>>>>>> Computer-go mailing list
>>>>>> Computer-go at computer-go.org
>>> Computer-go mailing list
>>> Computer-go at computer-go.org
>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