Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks

Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks.
Ruohan Zhang, Faraz Torabi, Garrett Warnell, and Peter Stone.
Autonomous Agents and Multi-Agent Systems, 35(31), June 2021.
official online version

Download

[PDF]3.8MB  

Abstract

A longstanding goal of artificial intelligence is to create artificial agentscapable of learning to perform tasks that require sequential decision making.Importantly, while it is the artificial agent that learns and acts, it is stillup to humans to specify the particular task to be performed. Classical task-specification approaches typically involve humans providing stationaryreward functions or explicit demonstrations of the desired tasks. However, therehas recently been a great deal of research energy invested in exploringalternative ways in which humans may guide learning agents that may, e.g., bemore suitable for certain tasks or require less human effort. This surveyprovides a high-level overview of five recent machine learning frameworks thatprimarily rely on human guidance apart from pre-specified reward functions orconventional, step-by-step action demonstrations. We review the motivation,assumptions, and implementation of each framework, and we discuss possiblefuture research directions.

BibTeX Entry

@article{JAAMAS21-Zhang,
author={Ruohan Zhang and Faraz Torabi and Garrett Warnell and Peter Stone},
title={Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks},
journal={Autonomous Agents and Multi-Agent Systems}, 
doi={10.1007/s10458-021-09514-w},
month="June",
year="2021",
volume="35",
number="31",
abstract = {
A longstanding goal of artificial intelligence is to create artificial agents
capable of learning to perform tasks that require sequential decision making.
Importantly, while it is the artificial agent that learns and acts, it is still
up to humans to specify the particular task to be performed. Classical 
task-specification approaches typically involve humans providing stationary
reward functions or explicit demonstrations of the desired tasks. However, there
has recently been a great deal of research energy invested in exploring
alternative ways in which humans may guide learning agents that may, e.g., be
more suitable for certain tasks or require less human effort. This survey
provides a high-level overview of five recent machine learning frameworks that
primarily rely on human guidance apart from pre-specified reward functions or
conventional, step-by-step action demonstrations. We review the motivation,
assumptions, and implementation of each framework, and we discuss possible
future research directions. 
},
wwwnote = {<a href="https://link.springer.com/article/10.1007/s10458-021-09514-w">official online version</a>},
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 17, 2021 22:18:57