Re: [Computer-go] Would a larger board (25x25) dramatically reduce AlphaGos skill?

2016-03-23 Thread Sighris
See below: On Tue, Mar 22, 2016 at 5:21 PM, Lukas van de Wiel < lukas.drinkt.t...@gmail.com> wrote: > It would reduce Alphago, because there is less training material in the > form of high-dan-games, to train the policy network. > Maybe not a concern. There has been a suggestion that AlphaGo

Re: [Computer-go] Would a larger board (25x25) dramatically reduce AlphaGos skill?

2016-03-22 Thread Yuancheng Luo
Conv net should be robust. From image processing domian, these are feature detectors (shape in case of go) that are invariant to translations (moving shape left right up down along board). Enlarging board wouldnt put bot at disadvantage in evaluating local positions. On Tuesday, March 22, 2016,

Re: [Computer-go] Would a larger board (25x25) dramatically reduce AlphaGos skill?

2016-03-22 Thread Ray Tayek
On 3/22/2016 5:21 PM, Lukas van de Wiel wrote: It would reduce Alphago, because there is less training material in the form of high-dan-games, to train the policy network. It would also reduce the skill of a human opponent, because (s)he would have less experience on a larger board, just as

Re: [Computer-go] Would a larger board (25x25) dramatically reduce AlphaGos skill?

2016-03-22 Thread Lukas van de Wiel
It would reduce Alphago, because there is less training material in the form of high-dan-games, to train the policy network. It would also reduce the skill of a human opponent, because (s)he would have less experience on a larger board, just as AlphaGo. It would be fun to see which can adapt

Re: [Computer-go] Would a larger board (25x25) dramatically reduce AlphaGos skill?

2016-03-22 Thread Ray Tayek
On 3/22/2016 11:25 AM, Tom M wrote: I suspect that even with a similarly large training sample for initialization that AlphaGo would suffer a major reduction in apparent skill level. i think a human would also. The CNN would require many more layers of convolution; the valuation of

Re: [Computer-go] Would a larger board (25x25) dramatically reduce AlphaGos skill?

2016-03-22 Thread uurtamo .
Ko is what makes this game difficult, from a theoretical point of view. I suspect ko+unresolved groups is where it's at. s. On Mar 22, 2016 11:25 AM, "Tom M" wrote: > I suspect that even with a similarly large training sample for > initialization that AlphaGo would suffer