BriefGPT.xyz
Jun, 2023
MuZero学习的模型是什么?
What model does MuZero learn?
HTML
PDF
Jinke He, Thomas M. Moerland, Frans A. Oliehoek
TL;DR
本文介绍了一种名为MuZero的深度模型强化学习算法,研究其深度学习模型的学习目标和用于策略改进的实用性,结果表明MuZero所学模型不能有效地推广到评估未知的策略,这限制了我们使用该模型进行计划进一步改善当前策略的程度。
Abstract
model-based reinforcement learning
has drawn considerable interest in recent years, given its promise to improve
sample efficiency
. Moreover, when using deep-learned models, it is potentially possible to learn co
→