AlphaGo Zero: Learning from scratch

Re:AlphaGo Zero: Learning from scratch by panic on Wednesday October 18, 2017 @02:24PM (#15501593)

Tree search is also used during play. In the paper, they pit the pure neural net against other versions of the algorithm -- it ends up slightly worse than the version that played Fan Hui, at about 3000 ELO.

[ Parent | on HN ]

Re:AlphaGo Zero: Learning from scratch by AlexCoventry on Wednesday October 18, 2017 @02:36PM (#15501724)

Oh, so it's just not using rollouts to estimate the board position? Thanks for the clarification.

[ Parent | on HN ]

Re:AlphaGo Zero: Learning from scratch by mrec on Thursday October 19, 2017 @05:27AM (#15506550)

It doesn't use rollouts at all:

> AlphaGo Zero does not use “rollouts” - fast, random games used by other Go programs to predict which player will win from the current board position. Instead, it relies on its high quality neural networks to evaluate positions.

[ Parent | on HN ]