Timeline for How do chess engines "think"?
Current License: CC BY-SA 3.0
14 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 6 at 3:23 | comment | added | dbdb | Well as long as we don't ask engine to share their high level concept in chess-land, they will indeed remain blackboxes. They are so, because we are content to say that. But the NN. weights are all there, training trajectories of them, along with all the training games. The probleme with getting the high level picture, is that it tends to slow down, or introduce bugs to make the internal model output information beyond best move at current positoin, regressions. The bottleneck is the objective criterion being not revised. Devs. optimize only for that. | |
| Mar 10, 2023 at 6:03 | comment | added | Cyriac Antony | To add to the comment of @InertialIgnorance, many machine learning (ML) based engines play against itself (or train with a game database). But, we have no idea how they actually 'think'; they are indeed blackboxes! | |
| Sep 29, 2019 at 0:21 | comment | added | Inertial Ignorance | Basically they search ahead with a search algorithm (e.g., minimax) and evaluate the positions using pre-programmed heuristics. Although some recent engines (e.g., AlphaZero) develop their own methods of evaluation through playing themselves. | |
| Sep 23, 2015 at 11:20 | answer | added | A passerby | timeline score: 3 | |
| Mar 19, 2014 at 13:36 | history | edited | user2001 |
tags
|
|
| Apr 25, 2013 at 8:57 | answer | added | bjedrzejewski | timeline score: 7 | |
| Apr 3, 2013 at 21:18 | vote | accept | chubbycantorset | ||
| Mar 27, 2013 at 13:52 | history | tweeted | twitter.com/#!/StackChess/status/316910706647773184 | ||
| Mar 27, 2013 at 0:16 | comment | added | Travis J | This is an awesome question, I really enjoyed the answers. | |
| Mar 26, 2013 at 22:34 | answer | added | Lynob | timeline score: 6 | |
| Mar 26, 2013 at 15:24 | answer | added | Daniel B | timeline score: 24 | |
| Mar 26, 2013 at 11:23 | comment | added | RemcoGerlich | Chess engines look at several million positions per second, so they can in fact look at all them until they get a few moves deep. | |
| Mar 26, 2013 at 5:32 | answer | added | Edward Goodson | timeline score: 28 | |
| Mar 26, 2013 at 5:17 | history | asked | chubbycantorset | CC BY-SA 3.0 |