{"id":"https://openalex.org/W3006033038","doi":"https://doi.org/10.1109/lra.2020.2972794","title":"Composing Diverse Policies for Temporally Extended Tasks","display_name":"Composing Diverse Policies for Temporally Extended Tasks","publication_year":2020,"publication_date":"2020-02-11","ids":{"openalex":"https://openalex.org/W3006033038","doi":"https://doi.org/10.1109/lra.2020.2972794","mag":"3006033038"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2020.2972794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2972794","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.08199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Daniel Angelov","orcid":"https://orcid.org/0000-0001-7292-5182"},"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":"Daniel Angelov","raw_affiliation_strings":["Institute of Perception, Action and Behaviour (IPAB), School of Informatics, The University of Edinburgh, Edinburgh, UK"],"raw_orcid":"https://orcid.org/0000-0001-7292-5182","affiliations":[{"raw_affiliation_string":"Institute of Perception, Action and Behaviour (IPAB), School of Informatics, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yordan Hristov","orcid":null},"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":"Yordan Hristov","raw_affiliation_strings":["Institute of Perception, Action and Behaviour (IPAB), School of Informatics, The University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Perception, Action and Behaviour (IPAB), School of Informatics, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Michael Burke","orcid":"https://orcid.org/0000-0001-7426-1498"},"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":"Michael Burke","raw_affiliation_strings":["Institute of Perception, Action and Behaviour (IPAB), School of Informatics, The University of Edinburgh, Edinburgh, UK"],"raw_orcid":"https://orcid.org/0000-0001-7426-1498","affiliations":[{"raw_affiliation_string":"Institute of Perception, Action and Behaviour (IPAB), School of Informatics, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":null,"display_name":"Subramanian Ramamoorthy","orcid":null},"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":"Subramanian Ramamoorthy","raw_affiliation_strings":["Institute of Perception, Action and Behaviour (IPAB), School of Informatics, The University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Perception, Action and Behaviour (IPAB), School of Informatics, The University of Edinburgh, Edinburgh, 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":1.3119,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79419494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5","issue":"2","first_page":"2658","last_page":"2665"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5867000222206116,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5867000222206116,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.21160000562667847,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.07639999687671661,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/robustness","display_name":"Robustness (evolution)","score":0.6585999727249146},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5364999771118164},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4758000075817108},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.462799996137619},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.451200008392334},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.44530001282691956},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43619999289512634},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4219000041484833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610999941825867},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6585999727249146},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5364999771118164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115000009536743},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.44530001282691956},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.4097999930381775},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.31610000133514404},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.30889999866485596},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25769999623298645}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/lra.2020.2972794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2972794","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1907.08199","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.08199","pdf_url":"https://arxiv.org/pdf/1907.08199","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:pure.ed.ac.uk:publications/ac358ead-a95b-4cf9-82ec-7483262b4a31","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/ac358ead-a95b-4cf9-82ec-7483262b4a31","pdf_url":"https://www.research.ed.ac.uk/files/135892374/Composing_Diverse_Policies_ANGELOV_DOA11012020_AFV.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Angelov, D, Hristov, Y, Burke, M & Ramamoorthy, S 2020, 'Composing Diverse Policies for Temporally Extended Tasks', IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 2658-2665. https://doi.org/10.1109/LRA.2020.2972794","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.08199","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.08199","pdf_url":"https://arxiv.org/pdf/1907.08199","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W130216483","https://openalex.org/W1592847719","https://openalex.org/W1981667747","https://openalex.org/W1986014385","https://openalex.org/W1994442991","https://openalex.org/W2020149918","https://openalex.org/W2034469604","https://openalex.org/W2050708324","https://openalex.org/W2073787051","https://openalex.org/W2100538121","https://openalex.org/W2107726111","https://openalex.org/W2109910161","https://openalex.org/W2132714442","https://openalex.org/W2136719407","https://openalex.org/W2141664020","https://openalex.org/W2466504495","https://openalex.org/W2769112066","https://openalex.org/W2789158833","https://openalex.org/W2925173345","https://openalex.org/W2935400569","https://openalex.org/W2963703448","https://openalex.org/W2964248288","https://openalex.org/W2964333597","https://openalex.org/W2967355195","https://openalex.org/W2968268581","https://openalex.org/W4230616527","https://openalex.org/W4245272388","https://openalex.org/W6629435415","https://openalex.org/W6630145856","https://openalex.org/W6630907848","https://openalex.org/W6635409453","https://openalex.org/W6675977238","https://openalex.org/W6687321610","https://openalex.org/W6704559304","https://openalex.org/W6740801417","https://openalex.org/W6744597842","https://openalex.org/W6745830540","https://openalex.org/W6752054832","https://openalex.org/W6752356361","https://openalex.org/W6754184789","https://openalex.org/W6756256016","https://openalex.org/W6760270490","https://openalex.org/W6761685526","https://openalex.org/W6762548593","https://openalex.org/W6763088550"],"related_works":[],"abstract_inverted_index":{"Robot":[0],"control":[1],"policies":[2,82,116],"for":[3,51],"temporally":[4,53],"extended":[5,54],"and":[6,32,67,90,108,161,165,193],"sequenced":[7],"tasks":[8,196],"are":[9,21],"often":[10,22],"characterized":[11],"by":[12],"discontinuous":[13],"switches":[14],"between":[15],"different":[16,62],"local":[17],"dynamics.":[18],"These":[19],"change-points":[20],"exploited":[23],"in":[24,117],"hierarchical":[25],"motion":[26,84,88],"planning":[27,85,139],"to":[28,33,46,113,126,156,159],"build":[29],"approximate":[30],"models":[31,107],"facilitate":[34],"the":[35,58,149,183,188],"design":[36],"of":[37,191],"local,":[38,103],"region-specific":[39],"controllers.":[40,93],"However,":[41],"it":[42],"becomes":[43],"combinatorially":[44],"challenging":[45],"implement":[47],"such":[48],"a":[49,75,96,118,133,138,168,177],"pipeline":[50],"complex":[52,170],"tasks,":[55],"especially":[56],"when":[57],"sub-controllers":[59],"work":[60],"on":[61,176],"information":[63],"streams,":[64],"time":[65],"scales":[66],"action":[68,160],"spaces.":[69],"In":[70],"this":[71],"letter,":[72],"we":[73],"introduce":[74,95],"method":[76],"that":[77,101,182],"can":[78],"automatically":[79],"compose":[80],"diverse":[81,115],"comprising":[83],"trajectories,":[86],"dynamic":[87],"primitives":[89],"neural":[91],"network":[92],"We":[94,122,146,180],"global":[97],"goal":[98],"scoring":[99],"estimator":[100],"uses":[102],"per-motion":[104],"primitive":[105],"dynamics":[106,163],"corresponding":[109],"activation":[110],"state-space":[111],"sets":[112],"sequence":[114,190],"locally":[119],"optimal":[120,189],"fashion.":[121],"use":[123],"expert":[124],"demonstrations":[125],"convert":[127],"what":[128],"is":[129],"typically":[130],"viewed":[131],"as":[132],"gradient-based":[134],"learning":[135],"process":[136,140],"into":[137],"without":[141],"explicitly":[142],"specifying":[143],"preand":[144],"post-conditions.":[145],"first":[147],"illustrate":[148],"proposed":[150,184],"framework":[151],"using":[152],"an":[153],"MDP":[154],"benchmark":[155],"showcase":[157],"robustness":[158],"model":[162],"mismatch,":[164],"then":[166],"with":[167],"particularly":[169],"physical":[171],"gear":[172],"assembly":[173],"task,":[174],"solved":[175],"PR2":[178],"robot.":[179],"show":[181],"approach":[185],"successfully":[186],"discovers":[187],"controllers":[192],"solves":[194],"both":[195],"efficiently.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-02-24T00:00:00"}