HackerTube 中文?

Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI | Lex Fridman Podcast #75

Lex FridmanYouTube ↗

Further reading 1

What if the best-scoring move is to pause the game? →Optimizing a score can reveal what its designer forgot to ask for.This video helps answer · What improved when visible mistakes declined?

Caption notes

Hutter distinguishes receiving occasional feedback from selecting a policy for its expected future reward. Neither operation by itself specifies which rewards a designer should assign.

Public machine transcript (may contain transcription errors) ↗
Original passages · 2
occasionally you give a reward signal
Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI | Lex Fridman Podcast #75 · ▶ 43:59–44:01
which leads in expectation
Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI | Lex Fridman Podcast #75 · ▶ 44:26–44:29

Hacker News comments

View original on HN ↗