How to Choose a Reinforcement-Learning Algorithm

How to Choose a Reinforcement-Learning Algorithm

The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we streamline the process of choosing reinforcement-learn...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bongratz, Fabian, Golkov, Vladimir, Mautner, Lukas, Della Libera, Luca, Heetmeyer, Frederik, Czaja, Felix, Rodemann, Julian, Cremers, Daniel
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Artificial Intelligence
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Statistics - Machine Learning
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Bongratz, Fabian
Golkov, Vladimir
Mautner, Lukas
Della Libera, Luca
Heetmeyer, Frederik
Czaja, Felix
Rodemann, Julian
Cremers, Daniel
description The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we streamline the process of choosing reinforcement-learning algorithms and action-distribution families. We provide a structured overview of existing methods and their properties, as well as guidelines for when to choose which methods. An interactive version of these guidelines is available online at https://rl-picker.github.io/.
doi_str_mv 10.48550/arxiv.2407.20917
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2407_20917</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2407_20917</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2407_209173</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjEw1zMysDQ052Qw8MgvVyjJV3DOyM8vTlVIVAhKzcxLyy9KTs1NzSvR9UlNLMrLzEtXcMxJzy_KLMnI5WFgTUvMKU7lhdLcDPJuriHOHrpgs-MLijJzE4sq40F2xIPtMCasAgAj-TCM</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>How to Choose a Reinforcement-Learning Algorithm</title><source>arXiv.org</source><creator>Bongratz, Fabian ; Golkov, Vladimir ; Mautner, Lukas ; Della Libera, Luca ; Heetmeyer, Frederik ; Czaja, Felix ; Rodemann, Julian ; Cremers, Daniel</creator><creatorcontrib>Bongratz, Fabian ; Golkov, Vladimir ; Mautner, Lukas ; Della Libera, Luca ; Heetmeyer, Frederik ; Czaja, Felix ; Rodemann, Julian ; Cremers, Daniel</creatorcontrib><description>The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we streamline the process of choosing reinforcement-learning algorithms and action-distribution families. We provide a structured overview of existing methods and their properties, as well as guidelines for when to choose which methods. An interactive version of these guidelines is available online at https://rl-picker.github.io/.</description><identifier>DOI: 10.48550/arxiv.2407.20917</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2024-07</creationdate><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,778,883</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2407.20917$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2407.20917$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Bongratz, Fabian</creatorcontrib><creatorcontrib>Golkov, Vladimir</creatorcontrib><creatorcontrib>Mautner, Lukas</creatorcontrib><creatorcontrib>Della Libera, Luca</creatorcontrib><creatorcontrib>Heetmeyer, Frederik</creatorcontrib><creatorcontrib>Czaja, Felix</creatorcontrib><creatorcontrib>Rodemann, Julian</creatorcontrib><creatorcontrib>Cremers, Daniel</creatorcontrib><title>How to Choose a Reinforcement-Learning Algorithm</title><description>The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we streamline the process of choosing reinforcement-learning algorithms and action-distribution families. We provide a structured overview of existing methods and their properties, as well as guidelines for when to choose which methods. An interactive version of these guidelines is available online at https://rl-picker.github.io/.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjEw1zMysDQ052Qw8MgvVyjJV3DOyM8vTlVIVAhKzcxLyy9KTs1NzSvR9UlNLMrLzEtXcMxJzy_KLMnI5WFgTUvMKU7lhdLcDPJuriHOHrpgs-MLijJzE4sq40F2xIPtMCasAgAj-TCM</recordid><startdate>20240730</startdate><enddate>20240730</enddate><creator>Bongratz, Fabian</creator><creator>Golkov, Vladimir</creator><creator>Mautner, Lukas</creator><creator>Della Libera, Luca</creator><creator>Heetmeyer, Frederik</creator><creator>Czaja, Felix</creator><creator>Rodemann, Julian</creator><creator>Cremers, Daniel</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20240730</creationdate><title>How to Choose a Reinforcement-Learning Algorithm</title><author>Bongratz, Fabian ; Golkov, Vladimir ; Mautner, Lukas ; Della Libera, Luca ; Heetmeyer, Frederik ; Czaja, Felix ; Rodemann, Julian ; Cremers, Daniel</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2407_209173</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Bongratz, Fabian</creatorcontrib><creatorcontrib>Golkov, Vladimir</creatorcontrib><creatorcontrib>Mautner, Lukas</creatorcontrib><creatorcontrib>Della Libera, Luca</creatorcontrib><creatorcontrib>Heetmeyer, Frederik</creatorcontrib><creatorcontrib>Czaja, Felix</creatorcontrib><creatorcontrib>Rodemann, Julian</creatorcontrib><creatorcontrib>Cremers, Daniel</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bongratz, Fabian</au><au>Golkov, Vladimir</au><au>Mautner, Lukas</au><au>Della Libera, Luca</au><au>Heetmeyer, Frederik</au><au>Czaja, Felix</au><au>Rodemann, Julian</au><au>Cremers, Daniel</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>How to Choose a Reinforcement-Learning Algorithm</atitle><date>2024-07-30</date><risdate>2024</risdate><abstract>The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we streamline the process of choosing reinforcement-learning algorithms and action-distribution families. We provide a structured overview of existing methods and their properties, as well as guidelines for when to choose which methods. An interactive version of these guidelines is available online at https://rl-picker.github.io/.</abstract><doi>10.48550/arxiv.2407.20917</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2407.20917
ispartof
issn
language eng
recordid cdi_arxiv_primary_2407_20917
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Statistics - Machine Learning
title How to Choose a Reinforcement-Learning Algorithm
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T14%3A39%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=How%20to%20Choose%20a%20Reinforcement-Learning%20Algorithm&rft.au=Bongratz,%20Fabian&rft.date=2024-07-30&rft_id=info:doi/10.48550/arxiv.2407.20917&rft_dat=%3Carxiv_GOX%3E2407_20917%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true