2009/5/1 Brian Sheppard <[email protected]>: > In reading Sylvain Gelly's thesis, it seemed that incorporating a prior > estimate of winning percentage is > very important to the practical strength of Mogo. > > E.g., with 10000 trials, Mogo achieved 2110 rating on CGOS, whereas my > program attempts to > reproduce existing research and is (maybe) 1900 rating with 20000 to 30000 > trials. The use of a > prior is an important difference, so I want to understand it more deeply. > > Some questions: > > 1) When you create a node, do you initialize > > number of simulations = C > number of wins = C * PriorEstimate() > > where C is a constant > 0? In Sylvain's thesis, the optimal C = 50, > suggesting that > incorporating a prior estimate was the equivalent of 50 UCT-RAVE trials. Yes, but for "number of RAVE simulations" and "number of RAVE wins". I think the optimal range was between 20 and 50 (you can test values in that range). The actual value certainly depends on your actual prior.
> 2) Two variations were suggested. In one variation, the prior was > incorporated into the UCT > statistics of the node. In the other, the prior was incorporated into the > RAVE statistics. Charts > in the thesis do not confirm which was actually being measured. In some > cases it appears to > be the UCT version, but elsewhere it seems to be the RAVE version. Does > anyone know > what was really done? Doing it on the RAVE statistics is what is working best. > 3) Elsewhere I have seen information suggesting that Mogo initializes RAVE > statistics to > implement progressive widening. Does that conflict with the use of a prior > for RAVE initialization, > or is it in addition to the use of a prior for RAVE initialization? Progressive widening and prior for RAVE initialization serve the same purpose. The prior is maybe smoother but they should be more or less equivalent in practice. > 4) When creating a node, do you estimate the prior for that node , or for > that node's children? I estimated the prior for all move for that node (I stored the RAVE values in the node, not in the children). Sylvain > Thanks in advance, > Brian > > _______________________________________________ > computer-go mailing list > [email protected] > http://www.computer-go.org/mailman/listinfo/computer-go/ > _______________________________________________ computer-go mailing list [email protected] http://www.computer-go.org/mailman/listinfo/computer-go/
