Books and journals Case studies Expert Briefings Open Access
Advanced search

A survey of inverse reinforcement learning techniques

Shao Zhifei (School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore)
Er Meng Joo (School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore)

International Journal of Intelligent Computing and Cybernetics

ISSN: 1756-378X

Publication date: 17 August 2012

Abstract

Purpose

–

This purpose of this paper is to provide an overview of the theoretical background and applications of inverse reinforcement learning (IRL).

Design/methodology/approach

–

Reinforcement learning (RL) techniques provide a powerful solution for sequential decision making problems under uncertainty. RL uses an agent equipped with a reward function to find a policy through interactions with a dynamic environment. However, one major assumption of existing RL algorithms is that reward function, the most succinct representation of the designer's intention, needs to be provided beforehand. In practice, the reward function can be very hard to specify and exhaustive to tune for large and complex problems, and this inspires the development of IRL, an extension of RL, which directly tackles this problem by learning the reward function through expert demonstrations. In this paper, the original IRL algorithms and its close variants, as well as their recent advances are reviewed and compared.

Findings

–

This paper can serve as an introduction guide of fundamental theory and developments, as well as the applications of IRL.

Originality/value

–

This paper surveys the theories and applications of IRL, which is the latest development of RL and has not been done so far.

Keywords

  • Inverse reinforcement learning
  • Reward function
  • Reinforcement learning
  • Artificial intelligence
  • Learning methods

Citation

Zhifei, S. and Meng Joo, E. (2012), "A survey of inverse reinforcement learning techniques", International Journal of Intelligent Computing and Cybernetics, Vol. 5 No. 3, pp. 293-311. https://doi.org/10.1108/17563781211255862

Download as .RIS

Publisher

:

Emerald Group Publishing Limited

Copyright © 2012, Emerald Group Publishing Limited

Please note you do not have access to teaching notes

You may be able to access teaching notes by logging in via Shibboleth, Open Athens or with your Emerald account.
Login
If you think you should have access to this content, click the button to contact our support team.
Contact us

To read the full version of this content please select one of the options below

You may be able to access this content by logging in via Shibboleth, Open Athens or with your Emerald account.
Login
To rent this content from Deepdyve, please click the button.
Rent from Deepdyve
If you think you should have access to this content, click the button to contact our support team.
Contact us
Emerald Publishing
  • Opens in new window
  • Opens in new window
  • Opens in new window
  • Opens in new window
© 2021 Emerald Publishing Limited

Services

  • Authors Opens in new window
  • Editors Opens in new window
  • Librarians Opens in new window
  • Researchers Opens in new window
  • Reviewers Opens in new window

About

  • About Emerald Opens in new window
  • Working for Emerald Opens in new window
  • Contact us Opens in new window
  • Publication sitemap

Policies and information

  • Privacy notice
  • Site policies
  • Modern Slavery Act Opens in new window
  • Chair of Trustees governance statement Opens in new window
  • COVID-19 policy Opens in new window
Manage cookies

We’re listening — tell us what you think

  • Something didn’t work…

    Report bugs here

  • All feedback is valuable

    Please share your general feedback

  • Member of Emerald Engage?

    You can join in the discussion by joining the community or logging in here.
    You can also find out more about Emerald Engage.

Join us on our journey

  • Platform update page

    Visit emeraldpublishing.com/platformupdate to discover the latest news and updates

  • Questions & More Information

    Answers to the most commonly asked questions here