HackerTube 中文?

30 Weird Chess Algorithms: Elo World

suckerpinchYouTube ↗

Further reading 1

What improved when a game agent got better? →A rising score might reflect a better network, deeper search or a loophole. Trace what the agent observes, what it tries and why the resulting move earns a reward.This video helps answer · Did the game agent see too little or optimize the wrong thing?

Caption notes

Compare chess agents that see occupied squares but cannot directly distinguish pieces. Games and Elo ratings test heuristics, search and learned board reconstruction.

Original passages · 6
it could learn a lot about the position just by trying out moves
30 Weird Chess Algorithms: Elo World · ▶ 4:21–5:01
this has to have some mistakes since the representation is ambiguous
30 Weird Chess Algorithms: Elo World · ▶ 32:02–32:08
this player performs significantly better than random due to its knowledge of openings but also significantly worse than the blinded players
30 Weird Chess Algorithms: Elo World · ▶ 38:07–38:15
making these engines better isn't gonna make them beat lousy any more often than always
30 Weird Chess Algorithms: Elo World · ▶ 39:29–39:37
the computer gets to see where the pieces are
30 Weird Chess Algorithms: Elo World · ▶ 2:00–2:07
the neural network predicts a board that's invalid
30 Weird Chess Algorithms: Elo World · ▶ 33:23–33:31

Hacker News comments

View original on HN ↗