Re: [Computer-go] GTX 1080 benchmark

2016-12-15 Thread Gian-Carlo Pascutto
On 15/12/2016 12:35, Hiroshi Yamashita wrote: > F32F128F256MNIST > GTX 1080 0.48ms 1.45ms 2.38ms 17sec, CUDA 8.0, cuDNN v5.0, Core i7 > 980X 3.3GHz 6core > GTX 1080 0.87ms 1.79ms 2.65ms 19sec, CUDA 8.0, cuDNN v5.1, Core i7 > 980X 3.3GHz 6core > GTX 980 0.60ms

Re: [Computer-go] Go Tournament with hinteresting rules

2016-12-15 Thread Darren Cook
> I have been told that bots that are based on MC play better when they only > record the result of each roll out (W or L) > rather than the margin of victory. > > To me this is counter-intuitive. > > Does anyone have an intelligible reason why it should be so? The search then optimizes for

Re: [Computer-go] Go Tournament with hinteresting rules

2016-12-15 Thread Lucas, Simon M
The intelligible reason is that focussing on the win or loss means that the bot is focussing on what actually matters: winning and not losing. If the bot focuses on the margin of victory the play can be skewed to aim for big wins that may not happen while paying insufficient attention to small