Re:Major advancements in Deep Learning in 2016
by feral on Wednesday December 07, 2016 @01:39PM
(#13124957)
I agree with this; I've seen people writing off AlphaGo as if it was very little new conceptually over MCTS (but just with more hardware). But the power of the NN was surprising.
There's a paragraph from the AlphoGo paper that I think speaks to this:
"We also tested against the strongest open-source Go program, Pachi, a sophisticated Monte-Carlo search program, ranked at 2 amateur dan on KGS, that executes 100,000 simulations per move. Using no search at all, the RL policy network won 85% of games against Pachi."
There's a paragraph from the AlphoGo paper that I think speaks to this:
"We also tested against the strongest open-source Go program, Pachi, a sophisticated Monte-Carlo search program, ranked at 2 amateur dan on KGS, that executes 100,000 simulations per move. Using no search at all, the RL policy network won 85% of games against Pachi."