{"id":"https://openalex.org/W4312285833","doi":"https://doi.org/10.1109/iros47612.2022.9981295","title":"Graph-Structured Policy Learning for Multi-Goal Manipulation Tasks","display_name":"Graph-Structured Policy Learning for Multi-Goal Manipulation Tasks","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312285833","doi":"https://doi.org/10.1109/iros47612.2022.9981295"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981295","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060590650","display_name":"David Klee","orcid":"https://orcid.org/0000-0003-1234-9755"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Klee","raw_affiliation_strings":["Khoury College of Computer Sciences, Northeastern University,Boston,MA,USA,02215"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences, Northeastern University,Boston,MA,USA,02215","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050593664","display_name":"Ond\u0159ej B\u00ed\u017ea","orcid":"https://orcid.org/0000-0003-3390-8050"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ondrej Biza","raw_affiliation_strings":["Khoury College of Computer Sciences, Northeastern University,Boston,MA,USA,02215"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences, Northeastern University,Boston,MA,USA,02215","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072578581","display_name":"Robert W. Platt","orcid":"https://orcid.org/0000-0002-5981-8443"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Platt","raw_affiliation_strings":["Khoury College of Computer Sciences, Northeastern University,Boston,MA,USA,02215"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences, Northeastern University,Boston,MA,USA,02215","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3508,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47162407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"33","issue":null,"first_page":"4765","last_page":"4772"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9987000226974487,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9641000032424927,"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/leverage","display_name":"Leverage (statistics)","score":0.8320289850234985},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7931710481643677},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7102451324462891},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.578318178653717},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5719667077064514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5550301671028137},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5460207462310791},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5342157483100891},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5318489074707031},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5303260684013367},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4823305308818817},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47963982820510864},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.46867451071739197},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4511992335319519},{"id":"https://openalex.org/keywords/goal-orientation","display_name":"Goal orientation","score":0.4500730633735657},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.44269484281539917},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3645029366016388},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3399314284324646}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8320289850234985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931710481643677},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7102451324462891},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.578318178653717},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5719667077064514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5550301671028137},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5460207462310791},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5342157483100891},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5318489074707031},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5303260684013367},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4823305308818817},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47963982820510864},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.46867451071739197},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4511992335319519},{"id":"https://openalex.org/C84653758","wikidata":"https://www.wikidata.org/wiki/Q5575175","display_name":"Goal orientation","level":2,"score":0.4500730633735657},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.44269484281539917},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3645029366016388},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3399314284324646},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981295","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1556824961","https://openalex.org/W2141841102","https://openalex.org/W2145339207","https://openalex.org/W2560674852","https://openalex.org/W2736337778","https://openalex.org/W2747329762","https://openalex.org/W2772269132","https://openalex.org/W2787066086","https://openalex.org/W2907424612","https://openalex.org/W2962736495","https://openalex.org/W2962746398","https://openalex.org/W2963262099","https://openalex.org/W2964036701","https://openalex.org/W2964227312","https://openalex.org/W2972758308","https://openalex.org/W3016361525","https://openalex.org/W3035847478","https://openalex.org/W3089482831","https://openalex.org/W3099815795","https://openalex.org/W3179146632","https://openalex.org/W3210940825","https://openalex.org/W3211108718","https://openalex.org/W4226088469","https://openalex.org/W4288021424","https://openalex.org/W4300799055","https://openalex.org/W6616173779","https://openalex.org/W6623316541","https://openalex.org/W6703271639","https://openalex.org/W6713200026","https://openalex.org/W6734215269","https://openalex.org/W6735789912","https://openalex.org/W6737937804","https://openalex.org/W6740801417","https://openalex.org/W6741302124","https://openalex.org/W6748012927","https://openalex.org/W6748599296","https://openalex.org/W6753060773","https://openalex.org/W6755289019","https://openalex.org/W6757865169","https://openalex.org/W6762640273","https://openalex.org/W6762722231","https://openalex.org/W6767649332","https://openalex.org/W6779651979","https://openalex.org/W6784257307","https://openalex.org/W6785308759","https://openalex.org/W6802171045","https://openalex.org/W6803403409"],"related_works":["https://openalex.org/W4402567770","https://openalex.org/W2569624374","https://openalex.org/W2965298293","https://openalex.org/W1607180678","https://openalex.org/W3201126466","https://openalex.org/W2081877814","https://openalex.org/W1905708401","https://openalex.org/W2745134424","https://openalex.org/W2440023763","https://openalex.org/W2962474440"],"abstract_inverted_index":{"Multi-goal":[0],"policy":[1,126],"learning":[2,59],"for":[3],"robotic":[4],"manipu-lation":[5],"is":[6],"challenging.":[7],"Prior":[8],"successes":[9],"have":[10],"used":[11],"state-based":[12],"representations":[13],"of":[14,33,43],"the":[15,34,71,90,125],"objects":[16],"or":[17],"provided":[18],"demonstration":[19],"data":[20],"to":[21,40,117],"facilitate":[22],"learning.":[23],"In":[24],"this":[25],"paper,":[26],"by":[27,68],"hand-coding":[28],"a":[29,49,94,108,131],"high-level":[30],"discrete":[31,91],"representation":[32],"domain,":[35],"we":[36,123],"show":[37],"that":[38,88,101],"policies":[39,63],"reach":[41],"dozens":[42],"goals":[44],"can":[45,104],"be":[46],"learned":[47,127],"with":[48,119],"single":[50],"network":[51],"using":[52],"Q-learning":[53],"from":[54],"pixels.":[55],"The":[56],"agent":[57],"focuses":[58],"on":[60,93,130],"simpler,":[61],"local":[62],"which":[64],"are":[65],"sequenced":[66],"together":[67],"planning":[69],"in":[70,128],"abstract":[72],"space.":[73],"We":[74,99],"compare":[75],"our":[76,102],"method":[77,103],"against":[78],"standard":[79],"multi-goal":[80],"RL":[81],"baselines,":[82],"as":[83,85],"well":[84],"other":[86],"methods":[87],"leverage":[89],"representation,":[92],"challenging":[95],"block":[96,111],"construction":[97],"domain.":[98],"find":[100],"build":[105],"more":[106],"than":[107],"hundred":[109],"different":[110],"structures,":[112],"and":[113],"demonstrate":[114],"forward":[115],"transfer":[116],"structures":[118],"novel":[120],"objects.":[121],"Lastly,":[122],"deploy":[124],"simulation":[129],"real":[132],"robot.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}