Openly accessible

Deep Reinforcement Learning with Interactive Feedback in a Human–Robot Environment

Moreira, Ithan, Rivas, Javier, Cruz Naranjo, Francisco, Dazeley, Richard, Ayala, Angel and Fernandes, Bruno 2020, Deep Reinforcement Learning with Interactive Feedback in a Human–Robot Environment, Applied Sciences, vol. 10, no. 16, pp. 1-16, doi: 10.3390/app10165574.

Attached Files
Name Description MIMEType Size Downloads

Title Deep Reinforcement Learning with Interactive Feedback in a Human–Robot Environment
Author(s) Moreira, Ithan
Rivas, Javier
Cruz Naranjo, FranciscoORCID iD for Cruz Naranjo, Francisco orcid.org/0000-0002-1131-3382
Dazeley, RichardORCID iD for Dazeley, Richard orcid.org/0000-0002-6199-9685
Ayala, Angel
Fernandes, Bruno
Journal name Applied Sciences
Volume number 10
Issue number 16
Article ID 5574
Start page 1
End page 16
Total pages 16
Publisher MDPI AG
Place of publication Basel, Switzerland
Publication date 2020
ISSN 2076-3417
Keyword(s) robotics
interactive deep
reinforcement learning
deep reinforcement learning
domestic scenario
Summary Robots are extending their presence in domestic environments every day, it being more common to see them carrying out tasks in home scenarios. In the future, robots are expected to increasingly perform more complex tasks and, therefore, be able to acquire experience from different sources as quickly as possible. A plausible approach to address this issue is interactive feedback, where a trainer advises a learner on which actions should be taken from specific states to speed up the learning process. Moreover, deep reinforcement learning has been recently widely used in robotics to learn the environment and acquire new skills autonomously. However, an open issue when using deep reinforcement learning is the excessive time needed to learn a task from raw input images. In this work, we propose a deep reinforcement learning approach with interactive feedback to learn a domestic task in a Human–Robot scenario. We compare three different learning methods using a simulated robotic arm for the task of organizing different objects; the proposed methods are (i) deep reinforcement learning (DeepRL); (ii) interactive deep reinforcement learning using a previously trained artificial agent as an advisor (agent–IDeepRL); and (iii) interactive deep reinforcement learning using a human advisor (human–IDeepRL). We demonstrate that interactive approaches provide advantages for the learning process. The obtained results show that a learner agent, using either agent–IDeepRL or human–IDeepRL, completes the given task earlier and has fewer mistakes compared to the autonomous DeepRL approach.
Language eng
DOI 10.3390/app10165574
Indigenous content off
HERDC Research category C1 Refereed article in a scholarly journal
Free to Read? Yes
Persistent URL http://hdl.handle.net/10536/DRO/DU:30141254

Connect to link resolver
 
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
Citation counts: TR Web of Science Citation Count  Cited 2 times in TR Web of Science
Scopus Citation Count Cited 3 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 40 Abstract Views, 1 File Downloads  -  Detailed Statistics
Created: Mon, 31 Aug 2020, 12:23:19 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.