Hyperparameters in Contextual RL are Highly Situational

Although Reinforcement Learning (RL) has shown impressive results in games and simulation, real-world application of RL suffers from its instability under changing environment conditions and hyperparameters. We give a first impression of the extent of this instability by showing that the hyperparame...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-12
Hauptverfasser: Eimer, Theresa, Benjamins, Carolin, Lindauer, Marius
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Eimer, Theresa
Benjamins, Carolin
Lindauer, Marius
description Although Reinforcement Learning (RL) has shown impressive results in games and simulation, real-world application of RL suffers from its instability under changing environment conditions and hyperparameters. We give a first impression of the extent of this instability by showing that the hyperparameters found by automatic hyperparameter optimization (HPO) methods are not only dependent on the problem at hand, but even on how well the state describes the environment dynamics. Specifically, we show that agents in contextual RL require different hyperparameters if they are shown how environmental factors change. In addition, finding adequate hyperparameter configurations is not equally easy for both settings, further highlighting the need for research into how hyperparameters influence learning and generalization in RL.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2756878860</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2756878860</sourcerecordid><originalsourceid>FETCH-proquest_journals_27568788603</originalsourceid><addsrcrecordid>eNqNyrsKwjAYQOEgCBbtOwScCzExl70oGZzUvWT4qykxibmAfXs7-ABOBw7fCjWUsUOnjpRuUJvzRAihQlLOWYOkniOkaJJ5QYGUsfW4D77Ap1Tj8PWCTQKs7ePpZnyzyyw2eON2aD0al6H9dYv259O9111M4V0hl2EKNS0wD1RyoaRSgrD_1Bce6TXw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2756878860</pqid></control><display><type>article</type><title>Hyperparameters in Contextual RL are Highly Situational</title><source>Freely Accessible Journals</source><creator>Eimer, Theresa ; Benjamins, Carolin ; Lindauer, Marius</creator><creatorcontrib>Eimer, Theresa ; Benjamins, Carolin ; Lindauer, Marius</creatorcontrib><description>Although Reinforcement Learning (RL) has shown impressive results in games and simulation, real-world application of RL suffers from its instability under changing environment conditions and hyperparameters. We give a first impression of the extent of this instability by showing that the hyperparameters found by automatic hyperparameter optimization (HPO) methods are not only dependent on the problem at hand, but even on how well the state describes the environment dynamics. Specifically, we show that agents in contextual RL require different hyperparameters if they are shown how environmental factors change. In addition, finding adequate hyperparameter configurations is not equally easy for both settings, further highlighting the need for research into how hyperparameters influence learning and generalization in RL.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Changing environments ; Machine learning ; Optimization</subject><ispartof>arXiv.org, 2022-12</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>781,785</link.rule.ids></links><search><creatorcontrib>Eimer, Theresa</creatorcontrib><creatorcontrib>Benjamins, Carolin</creatorcontrib><creatorcontrib>Lindauer, Marius</creatorcontrib><title>Hyperparameters in Contextual RL are Highly Situational</title><title>arXiv.org</title><description>Although Reinforcement Learning (RL) has shown impressive results in games and simulation, real-world application of RL suffers from its instability under changing environment conditions and hyperparameters. We give a first impression of the extent of this instability by showing that the hyperparameters found by automatic hyperparameter optimization (HPO) methods are not only dependent on the problem at hand, but even on how well the state describes the environment dynamics. Specifically, we show that agents in contextual RL require different hyperparameters if they are shown how environmental factors change. In addition, finding adequate hyperparameter configurations is not equally easy for both settings, further highlighting the need for research into how hyperparameters influence learning and generalization in RL.</description><subject>Changing environments</subject><subject>Machine learning</subject><subject>Optimization</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNyrsKwjAYQOEgCBbtOwScCzExl70oGZzUvWT4qykxibmAfXs7-ABOBw7fCjWUsUOnjpRuUJvzRAihQlLOWYOkniOkaJJ5QYGUsfW4D77Ap1Tj8PWCTQKs7ePpZnyzyyw2eON2aD0al6H9dYv259O9111M4V0hl2EKNS0wD1RyoaRSgrD_1Bce6TXw</recordid><startdate>20221221</startdate><enddate>20221221</enddate><creator>Eimer, Theresa</creator><creator>Benjamins, Carolin</creator><creator>Lindauer, Marius</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20221221</creationdate><title>Hyperparameters in Contextual RL are Highly Situational</title><author>Eimer, Theresa ; Benjamins, Carolin ; Lindauer, Marius</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27568788603</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Changing environments</topic><topic>Machine learning</topic><topic>Optimization</topic><toplevel>online_resources</toplevel><creatorcontrib>Eimer, Theresa</creatorcontrib><creatorcontrib>Benjamins, Carolin</creatorcontrib><creatorcontrib>Lindauer, Marius</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Eimer, Theresa</au><au>Benjamins, Carolin</au><au>Lindauer, Marius</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Hyperparameters in Contextual RL are Highly Situational</atitle><jtitle>arXiv.org</jtitle><date>2022-12-21</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Although Reinforcement Learning (RL) has shown impressive results in games and simulation, real-world application of RL suffers from its instability under changing environment conditions and hyperparameters. We give a first impression of the extent of this instability by showing that the hyperparameters found by automatic hyperparameter optimization (HPO) methods are not only dependent on the problem at hand, but even on how well the state describes the environment dynamics. Specifically, we show that agents in contextual RL require different hyperparameters if they are shown how environmental factors change. In addition, finding adequate hyperparameter configurations is not equally easy for both settings, further highlighting the need for research into how hyperparameters influence learning and generalization in RL.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2022-12
issn 2331-8422
language eng
recordid cdi_proquest_journals_2756878860
source Freely Accessible Journals
subjects Changing environments
Machine learning
Optimization
title Hyperparameters in Contextual RL are Highly Situational
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T06%3A36%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Hyperparameters%20in%20Contextual%20RL%20are%20Highly%20Situational&rft.jtitle=arXiv.org&rft.au=Eimer,%20Theresa&rft.date=2022-12-21&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2756878860%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2756878860&rft_id=info:pmid/&rfr_iscdi=true