News for hackers. Stuff that matters.

A comment on AlphaGo Zero: Learning from scratch. Parent comment

Re:AlphaGo Zero: Learning from scratch by feelix on Wednesday October 18, 2017 @02:47PM (#15501809)
It'd be particularly useful to have a chess bot that can play badly in the same way a human does.

The problem with the current chess bots is that they play badly, badly. They choose a terrible random mistake to make every few moves, while some of their other moves are brilliant. They cannot accurately mimic beginner or intermediate level players.

[ Parent | on HN ]
Re:AlphaGo Zero: Learning from scratch by thefalcon on Wednesday October 18, 2017 @05:11PM (#15503153)
This seems like something DeepMind could create, given the incentive. They were able to train AlphaGo to predict human moves in Go at a very high accuracy (obviously not with AlphaGo Zero, but the inferior human-predictive version is how they determined that AGZ is playing qualitatively differently).
[ Parent | on HN ]
Re:AlphaGo Zero: Learning from scratch by Florin_Andrei on Wednesday October 18, 2017 @02:54PM (#15501883)
In a sense, that would be like replicating the human brain's functionality, including the bugs and limitations.
[ Parent | on HN ]