Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning
The options framework in Hierarchical Reinforcement Learning breaks down overall goals into a combination of options or simpler tasks and associated policies, allowing for abstraction in the action space. Ideally, these options can be reused across different higher-level goals; indeed, such reuse is...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2022-06 |
---|---|
Hauptverfasser: | , , , , |
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 | Chauhan, Kushal Chatterjee, Soumya Reddy, Akash Ravindran, Balaraman Shenoy, Pradeep |
description | The options framework in Hierarchical Reinforcement Learning breaks down overall goals into a combination of options or simpler tasks and associated policies, allowing for abstraction in the action space. Ideally, these options can be reused across different higher-level goals; indeed, such reuse is necessary to realize the vision of a continual learning agent that can effectively leverage its prior experience. Previous approaches have only proposed limited forms of transfer of prelearned options to new task settings. We propose a novel option indexing approach to hierarchical learning (OI-HRL), where we learn an affinity function between options and the items present in the environment. This allows us to effectively reuse a large library of pretrained options, in zero-shot generalization at test time, by restricting goal-directed learning to only those options relevant to the task at hand. We develop a meta-training loop that learns the representations of options and environments over a series of HRL problems, by incorporating feedback about the relevance of retrieved options to the higher-level goal. We evaluate OI-HRL in two simulated settings - the CraftWorld and AI2THOR environments - and show that we achieve performance competitive with oracular baselines, and substantial gains over a baseline that has the entire option pool available for learning the hierarchical policy. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2676380450</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2676380450</sourcerecordid><originalsourceid>FETCH-proquest_journals_26763804503</originalsourceid><addsrcrecordid>eNqNjkEKwjAURIMgWLR3CLguxKSt3YtSQRGKewntr6bWn5qfgsc3igdwNfBmHsyERVKpVVKkUs5YTNQJIWS-llmmIlYdta9vBq_cDt5YJO4t95ruxEf64NMXJ3ts4AUNLw047YJR655XYLC1roYHoOcH0A6DsmDTVvcE8S_nbLnbnjdlMjj7HIH8pbOjw1Bdwo1cFSLNhPpv9QYvn0A2</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2676380450</pqid></control><display><type>article</type><title>Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning</title><source>Free E- Journals</source><creator>Chauhan, Kushal ; Chatterjee, Soumya ; Reddy, Akash ; Ravindran, Balaraman ; Shenoy, Pradeep</creator><creatorcontrib>Chauhan, Kushal ; Chatterjee, Soumya ; Reddy, Akash ; Ravindran, Balaraman ; Shenoy, Pradeep</creatorcontrib><description>The options framework in Hierarchical Reinforcement Learning breaks down overall goals into a combination of options or simpler tasks and associated policies, allowing for abstraction in the action space. Ideally, these options can be reused across different higher-level goals; indeed, such reuse is necessary to realize the vision of a continual learning agent that can effectively leverage its prior experience. Previous approaches have only proposed limited forms of transfer of prelearned options to new task settings. We propose a novel option indexing approach to hierarchical learning (OI-HRL), where we learn an affinity function between options and the items present in the environment. This allows us to effectively reuse a large library of pretrained options, in zero-shot generalization at test time, by restricting goal-directed learning to only those options relevant to the task at hand. We develop a meta-training loop that learns the representations of options and environments over a series of HRL problems, by incorporating feedback about the relevance of retrieved options to the higher-level goal. We evaluate OI-HRL in two simulated settings - the CraftWorld and AI2THOR environments - and show that we achieve performance competitive with oracular baselines, and substantial gains over a baseline that has the entire option pool available for learning the hierarchical policy.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Learning</subject><ispartof>arXiv.org, 2022-06</ispartof><rights>2022. 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><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Chauhan, Kushal</creatorcontrib><creatorcontrib>Chatterjee, Soumya</creatorcontrib><creatorcontrib>Reddy, Akash</creatorcontrib><creatorcontrib>Ravindran, Balaraman</creatorcontrib><creatorcontrib>Shenoy, Pradeep</creatorcontrib><title>Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning</title><title>arXiv.org</title><description>The options framework in Hierarchical Reinforcement Learning breaks down overall goals into a combination of options or simpler tasks and associated policies, allowing for abstraction in the action space. Ideally, these options can be reused across different higher-level goals; indeed, such reuse is necessary to realize the vision of a continual learning agent that can effectively leverage its prior experience. Previous approaches have only proposed limited forms of transfer of prelearned options to new task settings. We propose a novel option indexing approach to hierarchical learning (OI-HRL), where we learn an affinity function between options and the items present in the environment. This allows us to effectively reuse a large library of pretrained options, in zero-shot generalization at test time, by restricting goal-directed learning to only those options relevant to the task at hand. We develop a meta-training loop that learns the representations of options and environments over a series of HRL problems, by incorporating feedback about the relevance of retrieved options to the higher-level goal. We evaluate OI-HRL in two simulated settings - the CraftWorld and AI2THOR environments - and show that we achieve performance competitive with oracular baselines, and substantial gains over a baseline that has the entire option pool available for learning the hierarchical policy.</description><subject>Learning</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>eNqNjkEKwjAURIMgWLR3CLguxKSt3YtSQRGKewntr6bWn5qfgsc3igdwNfBmHsyERVKpVVKkUs5YTNQJIWS-llmmIlYdta9vBq_cDt5YJO4t95ruxEf64NMXJ3ts4AUNLw047YJR655XYLC1roYHoOcH0A6DsmDTVvcE8S_nbLnbnjdlMjj7HIH8pbOjw1Bdwo1cFSLNhPpv9QYvn0A2</recordid><startdate>20220612</startdate><enddate>20220612</enddate><creator>Chauhan, Kushal</creator><creator>Chatterjee, Soumya</creator><creator>Reddy, Akash</creator><creator>Ravindran, Balaraman</creator><creator>Shenoy, Pradeep</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>20220612</creationdate><title>Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning</title><author>Chauhan, Kushal ; Chatterjee, Soumya ; Reddy, Akash ; Ravindran, Balaraman ; Shenoy, Pradeep</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26763804503</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Chauhan, Kushal</creatorcontrib><creatorcontrib>Chatterjee, Soumya</creatorcontrib><creatorcontrib>Reddy, Akash</creatorcontrib><creatorcontrib>Ravindran, Balaraman</creatorcontrib><creatorcontrib>Shenoy, Pradeep</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & 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>Chauhan, Kushal</au><au>Chatterjee, Soumya</au><au>Reddy, Akash</au><au>Ravindran, Balaraman</au><au>Shenoy, Pradeep</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning</atitle><jtitle>arXiv.org</jtitle><date>2022-06-12</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>The options framework in Hierarchical Reinforcement Learning breaks down overall goals into a combination of options or simpler tasks and associated policies, allowing for abstraction in the action space. Ideally, these options can be reused across different higher-level goals; indeed, such reuse is necessary to realize the vision of a continual learning agent that can effectively leverage its prior experience. Previous approaches have only proposed limited forms of transfer of prelearned options to new task settings. We propose a novel option indexing approach to hierarchical learning (OI-HRL), where we learn an affinity function between options and the items present in the environment. This allows us to effectively reuse a large library of pretrained options, in zero-shot generalization at test time, by restricting goal-directed learning to only those options relevant to the task at hand. We develop a meta-training loop that learns the representations of options and environments over a series of HRL problems, by incorporating feedback about the relevance of retrieved options to the higher-level goal. We evaluate OI-HRL in two simulated settings - the CraftWorld and AI2THOR environments - and show that we achieve performance competitive with oracular baselines, and substantial gains over a baseline that has the entire option pool available for learning the hierarchical policy.</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, 2022-06 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2676380450 |
source | Free E- Journals |
subjects | Learning |
title | Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T08%3A37%3A24IST&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=Matching%20options%20to%20tasks%20using%20Option-Indexed%20Hierarchical%20Reinforcement%20Learning&rft.jtitle=arXiv.org&rft.au=Chauhan,%20Kushal&rft.date=2022-06-12&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2676380450%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2676380450&rft_id=info:pmid/&rfr_iscdi=true |