发帖
雷达卡
Towards Better Laplacian Representation in Reinforcement Learning with
Generalized Graph Drawing
Kaixin Wang * 1 Kuangqi Zhou * 1 Qixin Zhang 2 Jie Shao 3 Bryan Hooi 1 Jiashi Feng 1
Abstract
The Laplacian representation recently gains in-
creasing attention for reinforcement learning as it
provides succinct and informative representation
for states, by taking the eigenvectors of the Lapla-
cian matrix of the state-transition graph as state
em ...
京公网安备 11010802022788号
