Skip to main content
16 events
when toggle format what by license comment
S Jun 15, 2023 at 21:57 history edited SecretAgentMan CC BY-SA 4.0
deleted 14 characters in body
Jun 15, 2023 at 21:06 review Suggested edits
S Jun 15, 2023 at 21:57
Feb 18, 2021 at 15:51 history protected Brian Towers
Feb 18, 2021 at 14:35 comment added Joakim Quensel I am no chess player and I have no experience from computer chess but I find the topic interesting. From my logic (for what it's worth given my lack of experience) a chess computer used for support and training for a human chess player should evaluate a move based on a tree search that looks at the moves that are likely to be played by humans (you and your opponent) rather than theoretical "best" moves which gives a better positions after a series of moves that no humans would ever play (because the evaluation needed in order to find or conclude tgagbthese are really the best moves is beyond h
Nov 14, 2020 at 23:59 answer added pokep timeline score: 4
Nov 12, 2020 at 2:48 answer added Kenn Costales timeline score: 11
Sep 25, 2020 at 16:22 comment added Sopel human or non-human play is an illusion that's further fortified by beliefs.
Sep 24, 2020 at 6:48 answer added prusswan timeline score: 2
Sep 24, 2020 at 4:26 answer added jf328 timeline score: 4
Sep 23, 2020 at 21:58 answer added SmallChess timeline score: 3
Sep 16, 2020 at 21:44 answer added benrg timeline score: 4
Sep 16, 2020 at 18:32 answer added user24723 timeline score: 0
Sep 16, 2020 at 8:51 answer added friscodelrosario timeline score: -6
Sep 16, 2020 at 8:04 comment added wimi Maybe training a NN with a huge database of games played by such humans, so that the NN tries to predict the move the humans made based on the position? But it might well be that the existing databases are ridiculously small, given the large number of possible positions in chess...
Sep 16, 2020 at 7:46 review First posts
Sep 16, 2020 at 9:26
Sep 16, 2020 at 7:44 history asked Shakti CC BY-SA 4.0