dazeley-evaluationmethodology-2021.pdf (1.19 MB)
An Evaluation Methodology for Interactive Reinforcement Learning with Simulated Users
journal contribution
posted on 2021-01-01, 00:00 authored by Adam Bignold, Francisco Cruz, Richard DazeleyRichard Dazeley, Peter Vamplew, Cameron FoaleInteractive 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.
History
Journal
BiomimeticsVolume
6Issue
1Pagination
1 - 15Publisher
MDPILocation
Basel, SwitzerlandPublisher DOI
Link to full text
ISSN
2313-7673eISSN
2313-7673Language
engPublication classification
C1 Refereed article in a scholarly journalUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC