@inproceedings{jeon-etal-2021-interactive,
title = "Interactive Reinforcement Learning for Table Balancing Robot",
author = "Jeon, Haein and
Kim, Yewon and
Kang, Bo-Yeong",
editor = "Alikhani, Malihe and
Blukis, Valts and
Kordjamshidi, Parisa and
Padmakumar, Aishwarya and
Tan, Hao",
booktitle = "Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.splurobonlp-1.8",
doi = "10.18653/v1/2021.splurobonlp-1.8",
pages = "71--78",
abstract = "With the development of robotics, the use of robots in daily life is increasing, which has led to the need for anyone to easily train robots to improve robot use. Interactive reinforcement learning(IARL) is a method for robot training based on human{--}robot interaction; prior studies on IARL provide only limited types of feedback or require appropriately designed shaping rewards, which is known to be difficult and time-consuming. Therefore, in this study, we propose interactive deep reinforcement learning models based on voice feedback. In the proposed system, a robot learns the task of cooperative table balancing through deep Q-network using voice feedback provided by humans in real-time, with automatic speech recognition(ASR) and sentiment analysis to understand human voice feedback. As a result, an optimal policy convergence rate of up to 96{\%} was realized, and performance was improved in all voice feedback-based models",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jeon-etal-2021-interactive">
<titleInfo>
<title>Interactive Reinforcement Learning for Table Balancing Robot</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haein</namePart>
<namePart type="family">Jeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yewon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo-Yeong</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valts</namePart>
<namePart type="family">Blukis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parisa</namePart>
<namePart type="family">Kordjamshidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aishwarya</namePart>
<namePart type="family">Padmakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the development of robotics, the use of robots in daily life is increasing, which has led to the need for anyone to easily train robots to improve robot use. Interactive reinforcement learning(IARL) is a method for robot training based on human–robot interaction; prior studies on IARL provide only limited types of feedback or require appropriately designed shaping rewards, which is known to be difficult and time-consuming. Therefore, in this study, we propose interactive deep reinforcement learning models based on voice feedback. In the proposed system, a robot learns the task of cooperative table balancing through deep Q-network using voice feedback provided by humans in real-time, with automatic speech recognition(ASR) and sentiment analysis to understand human voice feedback. As a result, an optimal policy convergence rate of up to 96% was realized, and performance was improved in all voice feedback-based models</abstract>
<identifier type="citekey">jeon-etal-2021-interactive</identifier>
<identifier type="doi">10.18653/v1/2021.splurobonlp-1.8</identifier>
<location>
<url>https://aclanthology.org/2021.splurobonlp-1.8</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>71</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interactive Reinforcement Learning for Table Balancing Robot
%A Jeon, Haein
%A Kim, Yewon
%A Kang, Bo-Yeong
%Y Alikhani, Malihe
%Y Blukis, Valts
%Y Kordjamshidi, Parisa
%Y Padmakumar, Aishwarya
%Y Tan, Hao
%S Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F jeon-etal-2021-interactive
%X With the development of robotics, the use of robots in daily life is increasing, which has led to the need for anyone to easily train robots to improve robot use. Interactive reinforcement learning(IARL) is a method for robot training based on human–robot interaction; prior studies on IARL provide only limited types of feedback or require appropriately designed shaping rewards, which is known to be difficult and time-consuming. Therefore, in this study, we propose interactive deep reinforcement learning models based on voice feedback. In the proposed system, a robot learns the task of cooperative table balancing through deep Q-network using voice feedback provided by humans in real-time, with automatic speech recognition(ASR) and sentiment analysis to understand human voice feedback. As a result, an optimal policy convergence rate of up to 96% was realized, and performance was improved in all voice feedback-based models
%R 10.18653/v1/2021.splurobonlp-1.8
%U https://aclanthology.org/2021.splurobonlp-1.8
%U https://doi.org/10.18653/v1/2021.splurobonlp-1.8
%P 71-78
Markdown (Informal)
[Interactive Reinforcement Learning for Table Balancing Robot](https://aclanthology.org/2021.splurobonlp-1.8) (Jeon et al., splurobonlp 2021)
ACL
- Haein Jeon, Yewon Kim, and Bo-Yeong Kang. 2021. Interactive Reinforcement Learning for Table Balancing Robot. In Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics, pages 71–78, Online. Association for Computational Linguistics.