State-free Reinforcement Learning

In this work, we study the \textit{state-free RL} problem, where the algorithm does not have the states information before interacting with the environment. Specifically, denote the reachable state set by \({S}^\Pi := \{ s|\max_{\pi\in \Pi}q^{P, \pi}(s)>0 \}\), we design an algorithm which requir...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-09
Main Authors: Chen, Mingyu, Pacchiano, Aldo, Zhang, Xuezhou
Format: Article
Language:English
Subjects:
Algorithms
Parameters
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Chen, Mingyu
Pacchiano, Aldo
Zhang, Xuezhou
description In this work, we study the \textit{state-free RL} problem, where the algorithm does not have the states information before interacting with the environment. Specifically, denote the reachable state set by \({S}^\Pi := \{ s|\max_{\pi\in \Pi}q^{P, \pi}(s)>0 \}\), we design an algorithm which requires no information on the state space \(S\) while having a regret that is completely independent of \({S}\) and only depend on \({S}^\Pi\). We view this as a concrete first step towards \textit{parameter-free RL}, with the goal of designing RL algorithms that require no hyper-parameter tuning.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3111340780</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3111340780</sourcerecordid><originalsourceid>FETCH-proquest_journals_31113407803</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRQDC5JLEnVTStKTVUISs3MS8svSk7NTc0rUfBJTSzKy8xL52FgTUvMKU7lhdLcDMpuriHOHroFRfmFpanFJfFZ-aVFeUCpeGNDQ0NjEwNzCwNj4lQBAC3oLW8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3111340780</pqid></control><display><type>article</type><title>State-free Reinforcement Learning</title><source>Publicly Available Content (ProQuest)</source><creator>Chen, Mingyu ; Pacchiano, Aldo ; Zhang, Xuezhou</creator><creatorcontrib>Chen, Mingyu ; Pacchiano, Aldo ; Zhang, Xuezhou</creatorcontrib><description>In this work, we study the \textit{state-free RL} problem, where the algorithm does not have the states information before interacting with the environment. Specifically, denote the reachable state set by \({S}^\Pi := \{ s|\max_{\pi\in \Pi}q^{P, \pi}(s)&gt;0 \}\), we design an algorithm which requires no information on the state space \(S\) while having a regret that is completely independent of \({S}\) and only depend on \({S}^\Pi\). We view this as a concrete first step towards \textit{parameter-free RL}, with the goal of designing RL algorithms that require no hyper-parameter tuning.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Parameters</subject><ispartof>arXiv.org, 2024-09</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (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>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/3111340780?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Chen, Mingyu</creatorcontrib><creatorcontrib>Pacchiano, Aldo</creatorcontrib><creatorcontrib>Zhang, Xuezhou</creatorcontrib><title>State-free Reinforcement Learning</title><title>arXiv.org</title><description>In this work, we study the \textit{state-free RL} problem, where the algorithm does not have the states information before interacting with the environment. Specifically, denote the reachable state set by \({S}^\Pi := \{ s|\max_{\pi\in \Pi}q^{P, \pi}(s)&gt;0 \}\), we design an algorithm which requires no information on the state space \(S\) while having a regret that is completely independent of \({S}\) and only depend on \({S}^\Pi\). We view this as a concrete first step towards \textit{parameter-free RL}, with the goal of designing RL algorithms that require no hyper-parameter tuning.</description><subject>Algorithms</subject><subject>Parameters</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRQDC5JLEnVTStKTVUISs3MS8svSk7NTc0rUfBJTSzKy8xL52FgTUvMKU7lhdLcDMpuriHOHroFRfmFpanFJfFZ-aVFeUCpeGNDQ0NjEwNzCwNj4lQBAC3oLW8</recordid><startdate>20240927</startdate><enddate>20240927</enddate><creator>Chen, Mingyu</creator><creator>Pacchiano, Aldo</creator><creator>Zhang, Xuezhou</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>20240927</creationdate><title>State-free Reinforcement Learning</title><author>Chen, Mingyu ; Pacchiano, Aldo ; Zhang, Xuezhou</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31113407803</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Parameters</topic><toplevel>online_resources</toplevel><creatorcontrib>Chen, Mingyu</creatorcontrib><creatorcontrib>Pacchiano, Aldo</creatorcontrib><creatorcontrib>Zhang, Xuezhou</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content (ProQuest)</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>Chen, Mingyu</au><au>Pacchiano, Aldo</au><au>Zhang, Xuezhou</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>State-free Reinforcement Learning</atitle><jtitle>arXiv.org</jtitle><date>2024-09-27</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>In this work, we study the \textit{state-free RL} problem, where the algorithm does not have the states information before interacting with the environment. Specifically, denote the reachable state set by \({S}^\Pi := \{ s|\max_{\pi\in \Pi}q^{P, \pi}(s)&gt;0 \}\), we design an algorithm which requires no information on the state space \(S\) while having a regret that is completely independent of \({S}\) and only depend on \({S}^\Pi\). We view this as a concrete first step towards \textit{parameter-free RL}, with the goal of designing RL algorithms that require no hyper-parameter tuning.</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, 2024-09
issn 2331-8422
language eng
recordid cdi_proquest_journals_3111340780
source Publicly Available Content (ProQuest)
subjects Algorithms
Parameters
title State-free Reinforcement Learning
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T05%3A14%3A18IST&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=State-free%20Reinforcement%20Learning&rft.jtitle=arXiv.org&rft.au=Chen,%20Mingyu&rft.date=2024-09-27&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3111340780%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_31113407803%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3111340780&rft_id=info:pmid/&rfr_iscdi=true