{"id":"https://openalex.org/W2021004298","doi":"https://doi.org/10.1109/iros.2010.5650243","title":"Using dimensionality reduction to exploit constraints in reinforcement learning","display_name":"Using dimensionality reduction to exploit constraints in reinforcement learning","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W2021004298","doi":"https://doi.org/10.1109/iros.2010.5650243","mag":"2021004298"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2010.5650243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2010.5650243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://era.ed.ac.uk/bitstream/1842/3644/1/Using%20Dimensionality%20Reduction%20to%20Exploit%20Constraints%20in%20Reinforcement%20Learning.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102977758","display_name":"Sebastian Bitzer","orcid":"https://orcid.org/0000-0003-2713-4271"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"S Bitzer","raw_affiliation_strings":["School of Informatics, Informatics Forum, University of Edinburgh, UK","School of Informatics, University of Edinburgh, Informatics Forum, 10 Crichton Street, EH8 9AB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Informatics Forum, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Informatics Forum, 10 Crichton Street, EH8 9AB, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050881123","display_name":"Matthew Howard","orcid":"https://orcid.org/0000-0003-2534-4865"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"M Howard","raw_affiliation_strings":["School of Informatics, Informatics Forum, University of Edinburgh, UK","School of Informatics, University of Edinburgh, Informatics Forum, 10 Crichton Street, EH8 9AB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Informatics Forum, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Informatics Forum, 10 Crichton Street, EH8 9AB, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069715982","display_name":"Sethu Vijayakumar","orcid":"https://orcid.org/0000-0003-0649-7241"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"S Vijayakumar","raw_affiliation_strings":["School of Informatics, Informatics Forum, University of Edinburgh, UK","School of Informatics, University of Edinburgh, Informatics Forum, 10 Crichton Street, EH8 9AB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Informatics Forum, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Informatics Forum, 10 Crichton Street, EH8 9AB, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.9076,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.86910229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3219","last_page":"3225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8592305779457092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7546789646148682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6956852078437805},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6722724437713623},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6404041647911072},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6393842697143555},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6342216730117798},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5872495770454407},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.584844172000885},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5832775235176086},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.48593035340309143},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4773847460746765},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4636351466178894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08581432700157166},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.08533000946044922}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8592305779457092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7546789646148682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6956852078437805},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6722724437713623},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6404041647911072},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6393842697143555},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6342216730117798},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5872495770454407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.584844172000885},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5832775235176086},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.48593035340309143},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4773847460746765},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4636351466178894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08581432700157166},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.08533000946044922},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/iros.2010.5650243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2010.5650243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/3644","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3644","pdf_url":"https://era.ed.ac.uk/bitstream/1842/3644/1/Using%20Dimensionality%20Reduction%20to%20Exploit%20Constraints%20in%20Reinforcement%20Learning.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.170.2746","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.170.2746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/svijayak/publications/bitzer-IROS2010.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.710.2424","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.2424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.inf.kcl.ac.uk/staff/mhoward/pdf/Bitzer2010.pdf","raw_type":"text"},{"id":"pmh:oai:escidoc.org:escidoc:773622","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0011-2803-E","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/959a5657-9bb1-4d7f-8855-f75c919dddd6","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/959a5657-9bb1-4d7f-8855-f75c919dddd6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bitzer, S, Howard, M & Vijayakumar, S 2010, Using Dimensionality Reduction to Exploit Constraints in Reinforcement Learning. in 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). N/A edn, vol. N/A, Piscataway, N.J., pp. 3219-3225. https://doi.org/10.1109/IROS.2010.5650243","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/3644","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3644","pdf_url":"https://era.ed.ac.uk/bitstream/1842/3644/1/Using%20Dimensionality%20Reduction%20to%20Exploit%20Constraints%20in%20Reinforcement%20Learning.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2021004298.pdf","grobid_xml":"https://content.openalex.org/works/W2021004298.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1592847719","https://openalex.org/W1593430322","https://openalex.org/W1663973292","https://openalex.org/W1746819321","https://openalex.org/W2080040630","https://openalex.org/W2081864293","https://openalex.org/W2097944344","https://openalex.org/W2108535023","https://openalex.org/W2118858375","https://openalex.org/W2121863487","https://openalex.org/W2129515556","https://openalex.org/W2136111243","https://openalex.org/W2148277778","https://openalex.org/W2397240726","https://openalex.org/W4211049957","https://openalex.org/W4212863985","https://openalex.org/W4214717370","https://openalex.org/W4233512036","https://openalex.org/W4249441547","https://openalex.org/W6676557315","https://openalex.org/W6680375596","https://openalex.org/W6712173889"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W1995622179","https://openalex.org/W4391160746"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,94,138],"in":[2,8,34,90,96,109,120],"the":[3,32,39,67,91,97,106,125,131,144],"high-dimensional,":[4],"continuous":[5],"spaces":[6],"typical":[7],"robotics,":[9],"remains":[10],"a":[11,18,46,110,139],"challenging":[12],"problem.":[13],"To":[14],"overcome":[15],"this":[16,123],"challenge,":[17],"popular":[19],"approach":[20,136],"has":[21],"been":[22],"to":[23,26,37,44,54,71,85,104],"use":[24,80],"demonstrations":[25,59],"find":[27,45,72],"an":[28,35,51,73],"appropriate":[29],"initialisation":[30],"of":[31,41,60],"policy":[33],"attempt":[36],"reduce":[38],"number":[40],"iterations":[42],"needed":[43,127],"solution.":[47],"Here,":[48],"we":[49,79,101],"present":[50,89],"alternative":[52],"way":[53],"incorporate":[55],"prior":[56],"knowledge":[57],"from":[58],"individual":[61],"postures":[62],"into":[63],"learning,":[64],"by":[65],"extracting":[66],"inherent":[68],"problem":[69,108],"structure":[70],"efficient":[74],"state":[75],"representation.":[76],"In":[77],"particular,":[78],"probabilistic,":[81],"nonlinear":[82],"dimensionality":[83],"reduction":[84],"capture":[86],"latent":[87,99],"constraints":[88],"data.":[92],"By":[93],"policies":[95],"learnt":[98],"space,":[100],"are":[102],"able":[103],"solve":[105],"planning":[107],"reduced":[111],"space":[112],"that":[113],"automatically":[114],"satisfies":[115],"task":[116,142],"constraints.":[117],"As":[118],"shown":[119],"our":[121,135],"experiments,":[122],"reduces":[124],"exploration":[126],"and":[128],"greatly":[129],"accelerates":[130],"learning.":[132],"We":[133],"demonstrate":[134],"for":[137],"bimanual":[140],"reaching":[141],"on":[143],"19-DOF":[145],"KHR-1HV":[146],"humanoid.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2025-10-10T00:00:00"}