An Evaluation Methodology for Interactive Reinforcement Learning with Simulated Users Bignold, A, Cruz, F, Dazeley, Richard, Vamplew, P and Foale, C 2021, An Evaluation Methodology for Interactive Reinforcement Learning with Simulated Users, Biomimetics, vol. 6, no. 1, pp. 1-15, doi: 10.3390/biomimetics6010013. Attached Files Name Description MIMEType Size Downloads dazeley-evaluationmethodology-2021.pdf Published version application/pdf 1.18MB 5 Title An Evaluation Methodology for Interactive Reinforcement Learning with Simulated Users Author(s) Bignold, A Cruz, F Dazeley, Richard orcid.org/0000-0002-6199-9685 Vamplew, P Foale, C Journal name Biomimetics Volume number 6 Issue number 1 Start page 1 End page 15 Total pages 15 Publisher MDPI Place of publication Basel, Switzerland Publication date 2021 ISSN 2313-7673 2313-7673 Keyword(s) interactive reinforcement learning methodology for simulated users reinforcement learning reward shaping Summary Interactive reinforcement learning methods utilise an external information source to evaluate decisions and accelerate learning. Previous work has shown that human advice could significantly improve learning agents’ performance. When evaluating reinforcement learning algorithms, it is common to repeat experiments as parameters are altered or to gain a sufficient sample size. In this regard, to require human interaction every time an experiment is restarted is undesirable, particularly when the expense in doing so can be considerable. Additionally, reusing the same people for the experiment introduces bias, as they will learn the behaviour of the agent and the dynamics of the environment. This paper presents a methodology for evaluating interactive reinforcement learning agents by employing simulated users. Simulated users allow human knowledge, bias, and interaction to be simulated. The use of simulated users allows the development and testing of reinforcement learning agents, and can provide indicative results of agent performance under defined human constraints. While simulated users are no replacement for actual humans, they do offer an affordable and fast alternative for evaluative assisted agents. We introduce a method for performing a preliminary evaluation utilising simulated users to show how performance changes depending on the type of user assisting the agent. Moreover, we describe how human interaction may be simulated, and present an experiment illustrating the applicability of simulating users in evaluating agent performance when assisted by different types of trainers. Experimental results show that the use of this methodology allows for greater insight into the performance of interactive reinforcement learning agents when advised by different users. The use of simulated users with varying characteristics allows for evaluation of the impact of those characteristics on the behaviour of the learning agent. Language eng DOI 10.3390/biomimetics6010013 Indigenous content off HERDC Research category C1 Refereed article in a scholarly journal Free to Read? Yes Use Rights Persistent URL http://hdl.handle.net/10536/DRO/DU:30148126 Document type: Journal Article Collections: Faculty of Science, Engineering and Built Environment School of Information Technology Open Access Collection Related Links Link Description Link to full-text (open access)     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au. Versions Version Filter Type Thu, 18 Feb 2021, 08:06:46 EST Fri, 19 Feb 2021, 04:01:44 EST Fri, 19 Feb 2021, 05:04:25 EST Mon, 22 Feb 2021, 14:08:07 EST Mon, 22 Feb 2021, 14:09:32 EST Mon, 22 Feb 2021, 15:04:19 EST Mon, 01 Mar 2021, 09:40:18 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 0 times in Scopus Search Google Scholar Access Statistics: 11 Abstract Views, 6 File Downloads  -  Detailed Statistics Created: Thu, 18 Feb 2021, 08:06:46 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.