BriefGPT.xyz
Jun, 2012
具有形式学习时间保证的增量式基于模型的学习器
Incremental Model-based Learners With Formal Learning-Time Guarantees
HTML
PDF
Alexander L. Strehl, Lihong Li, Michael L. Littman
TL;DR
研究了使用实时动态规划加速基于模型的学习算法，提高了在求解有限状态和动作空间的马尔可夫决策问题时的计算效率，并在 PAC 意义下证明了这两种算法的高效性。
Abstract
model-based learning
algorithms have been shown to use experience efficiently when learning to solve
markov decision processes
(MDPs) with finite state and action spaces. However, their high computational cost du
→