One Learning to RL them all:
— Yann LeCun (@ylecun) December 4, 2020
ReBeL (Recursive Belief-based Learning) is a general RL+Search method that works for all two-player zero-sum games, including imperfect-information games (poker, liar's dice,...) and perfect-information games (chess, go....). https://t.co/2sw8Zbe8rg
from Twitter https://twitter.com/ylecun
December 04, 2020 at 06:02AM
via IFTTT
No comments:
Post a Comment