reversi-alpha-zero icon indicating copy to clipboard operation
reversi-alpha-zero copied to clipboard

About the optimizer?

Open wjllance opened this issue 7 years ago • 5 comments

  1. I found that the optimizer only load data at the beginning, will it reload new play data in the training progress? 2.Hope more log can be available, such as loss with step

wjllance avatar Dec 27 '17 06:12 wjllance

better divide log into different file, haha

wjllance avatar Dec 27 '17 07:12 wjllance

Hi @wjllance

  1. I found that the optimizer only load data at the beginning, will it reload new play data in the training progress?

The optimizer reloads new play data at here.

2.Hope more log can be available, such as loss with step better divide log into different file,

Surely. I think so too :)

mokemokechicken avatar Dec 27 '17 23:12 mokemokechicken

So when the trainer pick a batch, it will pick from all the old data, without ignoring the very begging play data, right? If we can produce more self play data, maybe it's a better way to select from most recent data, does it make sense?

wjllance avatar Dec 28 '17 16:12 wjllance

So when the trainer pick a batch, it will pick from all the old data, without ignoring the very begging play data, right?

Right. Trainer picks up all data.

If we can produce more self play data, maybe it's a better way to select from most recent data, does it make sense?

The old data will be removed by self-play at here.

config.play_data.max_file_num decides how many old data are remained.

mokemokechicken avatar Dec 29 '17 00:12 mokemokechicken

oh thx, you're so nice~

wjllance avatar Dec 29 '17 02:12 wjllance