use board symmetry

[PascalCremer]

No description provided.

[harbecke]

we could apply all filters rotated by 180°, i've never done sth like this though

[PascalCremer]

or you could just rotate the input and output which is simply taking each board vector reversed. harbecke <notifications@github.com> schrieb am Mo., 11. März 2019, 13:03:

…

we could apply all filters rotated by 180°, i've never done sth like this though — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#6 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ADGqn4mMiHKsntM6kSWmQAapDmCO87Kpks5vVkYXgaJpZM4balt5> .

[harbecke]

so you want to use board symmetry for training, not enforcing evaluation symmetry?

[PascalCremer]

alphago zero uses both. they enhace training data by a factor of 8 using the 8 symmetric go boards and use a randomly selected board during network evaluation. I would fiest implement it for data generation as this is the bottleneck for MCTS models. harbecke <notifications@github.com> schrieb am Mo., 11. März 2019, 15:01:

…

so you want to use board symmetry for training, not enforcing evaluation symmetry? — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#6 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ADGqnwg2EUhmYC0AvAjzubPAkIysCTP5ks5vVmHSgaJpZM4balt5> .

[PascalCremer]

Implemented in SelfPlayGenerator for MCTS self play data creation