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...

Full description

Bibliographic Details

Published in:	American Statistician Vol. 77; no. 2; pp. 223 - 234
Main Authors:	Tec, Mauricio, Duan, Yunshan, Müller, Peter
Format:	Article
Published:	Taylor & Francis Ltd May2023
Subjects:	Reward (Psychology) Active learning Optimal stopping (Mathematical statistics) Reinforcement learning Sequential learning Experimental design Statistical decision making
Online Access:	View this record in EBSCOhost