Giga Chang comments

Results 8 comments of


                                            Giga Chang

Use multiprocess to speed up training and playing.

Hi @JernejHabjan , Thank you for found this bug. I push a new commit to fix this bug. Can you try again? Thanks!

Use multiprocess to speed up training and playing.

> Is there any chance I can use this during training? Yes, I have a multiprocess version to speed up training. Maybe I can make a new PR after this...

Use multiprocess to speed up training and playing.

@51616 It is not possible to get 2 times faster with only 2 cores. Here are some record of self-play time with my multiprocess version. Game: 6x6 Othello numEps: 128...

Use multiprocess to speed up training and playing.

@51616 I commit the multiprocess training version. It takes 2 minutes 20 seconds to training 6x6 Othello with 25 simulations in 4 cores and the original version takes 3 minutes...

Use multiprocess to speed up training and playing.

@51616 Yes, I parallel play many games during self-play not MCTS, because it's very difficult to implement multi-thread MCTS. In my case, I use ResNet as my NN and it...

Use multiprocess to speed up training and playing.

@51616 That's my bad. Ideally, it should create many self-play process and one model process. When each self-play process need predict initial policy and value during searching, it should call...

Use multiprocess to speed up training and playing.

Hi @51616 and @im0qianqian , thanks for your reply. I commit a new version of my mutliprocess version. Now, each process play many games instead 1 game. So do not...

Use multiprocess to speed up training and playing.

@im0qianqian I think this is **alpha-zero-general**'s problem. For now, the result of MCTS does not have randomness. It will make MCTS always make same move when playing if we always...