A Comparative Tutorial of Bayesian Sequential Design and Reinforcement Learning.

Reinforcement learning (RL) is a computational approach to reward-driven learning in sequential decision problems. It implements the discovery of optimal actions by learning from an agent interacting with an environment rather than from supervised data. We contrast and compare RL with traditional se...

Descripción completa

Detalles Bibliográficos

Publicado en:	American Statistician Vol. 77; no. 2; pp. 223 - 234
Autores principales:	Tec, Mauricio, Duan, Yunshan, Müller, Peter
Formato:	Artículo
Publicado:	Taylor & Francis Ltd May2023
Materias:	Reward (Psychology) Active learning Optimal stopping (Mathematical statistics) Reinforcement learning Sequential learning Experimental design Statistical decision making
Acceso en línea:	Ver este registro en EBSCOhost