News for hackers. Stuff that matters.

A comment on Human-like neural network chess engine trained on lichess games. Parent comment

Re:Human-like neural network chess engine trained on lichess... by sweezyjeezy on Sunday January 17, 2021 @10:40AM (#25811542)
This makes perfect sense - but is a bit problematic given the intended goal of the project. They've built a bot that plays like an 'averaged group' of humans, not a human. Maybe they need a better way of sampling from the outputs.
[ Parent | on HN ]
Re:Human-like neural network chess engine trained on lichess... by stingraycharles on Sunday January 17, 2021 @12:48PM (#25812903)
This is always the problem with training from historical data only: you’ll become very good at being just as good as the sample group.

Ideally you just use the sample as the basis, and then let an AI engine play against itself for training, and/or participate in real world games, such as they did with AlphaGo and/or AlphaStar.

[ Parent | on HN ]
Re:Human-like neural network chess engine trained on lichess... by stoat_meniscus on Sunday January 17, 2021 @04:57PM (#25815469)
Seems analogous to the average faces photography project where the composite faces of a large number of men or women end up being more attractive than you'd imagine for an average person.
[ Parent | on HN ]