Hi Robert, maybe it's just me, but you seem to come off as perhaps a little too aggressive in your recent few emails...
On Tue, Feb 02, 2016 at 09:35:14AM +0100, Robert Jasiek wrote: > On 01.02.2016 23:01, Brian Cloutier wrote:> I had to search a lot of papers > on MCTS which > > mentioned "terminal states" before finding one which defined them. > > [...] they defined it as a position where there are no more legal > > moves. > > On 01.02.2016 23:15, Brian Sheppard wrote: > >You play until neither player wishes to make a move. The players > > are willing to move on any point that is not self-atari, and they > >are willing to make self-atari plays if capture would result in a > >Nakade (http://senseis.xmp.net/?Nakade) > > Defining "terminal state" as no more legal moves is probably inappropriate. > The phrase "willing to move" is undefined, unless they exactly define it as > "to make self-atari plays iff capture would result in a Nakade". This > requires a proof that this is the only exception. Where is that proof? It > also requires a definition of nakade. Where is that definition? The question was about the practical implementation of an MC simulation, which does *not* require formal definitions of all concepts used in the description, or any proofs. It's just a heuristic, and it can be arbitrarily complicated, making a tradeoff between speed and accuracy. My definition of this state is in the (quite literal) code https://github.com/pasky/pachi/blob/master/tactics/selfatari.c#L638 It's the most complicated part of Pachi. :-) (And doesn't really work that well either.) But it covers a lot of cases. To the subject at hand, I'd suggest a lot simpler approach if the DCNN is itself capable of avoiding the bad self-ataris. Just do not restrict the DCNN in any way and have a separate check that stops the playout if all the remaining moves are self-atari in the most trivial sense of the word. This means that you stop the game too early if the whole board is filled (including dame and territory) but some nakade or throwin remains that the DCNN would like to play out, but I suspect that would pretty much never happen in practice? -- Petr Baudis If you have good ideas, good data and fast computers, you can do almost anything. -- Geoffrey Hinton _______________________________________________ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
