{"id":"https://openalex.org/W4312866209","doi":"https://doi.org/10.1109/iros47612.2022.9982278","title":"Multi-Objective Policy Gradients with Topological Constraints","display_name":"Multi-Objective Policy Gradients with Topological Constraints","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312866209","doi":"https://doi.org/10.1109/iros47612.2022.9982278"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9982278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9982278","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":"conference-paper","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/A5013249239","display_name":"Kyle Hollins Wray","orcid":"https://orcid.org/0000-0001-6986-9941"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Hollins Wray","raw_affiliation_strings":["Stanford University,Stanford,CA,USA","Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046771851","display_name":"Stas Tiomkin","orcid":"https://orcid.org/0000-0003-3677-6874"},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stas Tiomkin","raw_affiliation_strings":["San Jose State University,CA,USA","San Jose State University, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"San Jose State University,CA,USA","institution_ids":["https://openalex.org/I51504820"]},{"raw_affiliation_string":"San Jose State University, CA, USA","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068326377","display_name":"Mykel J. Kochenderfer","orcid":"https://orcid.org/0000-0002-7238-9663"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mykel J. Kochenderfer","raw_affiliation_strings":["Stanford University,Stanford,CA,USA","Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["University of California,Berkeley,CA,USA","University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley,CA,USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9034","last_page":"9039"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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":0.9897000193595886,"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"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7480080127716064},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.627588152885437},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6221259832382202},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6083287000656128},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5838379263877869},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5309457778930664},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5212055444717407},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5023543834686279},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5017590522766113},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4497987926006317},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4338603615760803},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.42269057035446167},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4046071767807007},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.3774980902671814},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3525354266166687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3356744647026062},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.250112920999527},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17481300234794617}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7480080127716064},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.627588152885437},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6221259832382202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6083287000656128},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5838379263877869},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5309457778930664},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5212055444717407},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5023543834686279},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5017590522766113},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4497987926006317},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4338603615760803},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.42269057035446167},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4046071767807007},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.3774980902671814},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3525354266166687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3356744647026062},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.250112920999527},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17481300234794617},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9982278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9982278","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":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1518931405","https://openalex.org/W1999874108","https://openalex.org/W2040306558","https://openalex.org/W2117428849","https://openalex.org/W2155027007","https://openalex.org/W2215828449","https://openalex.org/W2736601468","https://openalex.org/W2739957299","https://openalex.org/W2907537824","https://openalex.org/W2955562763","https://openalex.org/W2963311874","https://openalex.org/W3034840734","https://openalex.org/W3210110380","https://openalex.org/W4214717370","https://openalex.org/W4285102131","https://openalex.org/W4293545785","https://openalex.org/W6638018090","https://openalex.org/W6683204974","https://openalex.org/W6741002519","https://openalex.org/W6757380569"],"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/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"Multi-objective":[0],"optimization":[1,117],"models":[2],"that":[3,84],"encode":[4],"ordered":[5],"sequential":[6],"constraints":[7],"provide":[8],"a":[9,20,100,104,110,124,140],"solution":[10],"to":[11],"model":[12],"various":[13],"challenging":[14],"problems":[15,41],"including":[16],"encoding":[17],"preferences,":[18],"modeling":[19],"curriculum,":[21],"and":[22,48,59,66,88,138],"enforcing":[23],"measures":[24],"of":[25,31,40,45,80,113,133],"safety.":[26],"A":[27],"recently":[28],"developed":[29],"theory":[30],"topological":[32],"Markov":[33],"decision":[34],"processes":[35],"(TMDPs)":[36],"captures":[37],"this":[38,51,122],"range":[39],"for":[42,72,103],"the":[43,68,78,114],"case":[44],"discrete":[46],"states":[47],"actions.":[49],"In":[50],"work,":[52],"we":[53,98],"extend":[54],"TMDPs":[55,108],"towards":[56],"continuous":[57],"spaces":[58],"unknown":[60],"transition":[61],"dynamics":[62],"by":[63,109],"formulating,":[64],"proving,":[65],"implementing":[67],"policy":[69,105,116],"gradient":[70,106],"theorem":[71],"TMDPs.":[73],"This":[74],"theoretical":[75],"result":[76],"enables":[77],"creation":[79],"TMDP":[81],"learning":[82,94],"algorithms":[83],"use":[85],"function":[86],"approximators,":[87],"can":[89],"generalize":[90],"existing":[91],"deep":[92],"reinforcement":[93],"(DRL)":[95],"approaches.":[96],"Specifically,":[97],"present":[99],"new":[101],"algorithm":[102],"in":[107,136],"simple":[111],"extension":[112],"proximal":[115],"(PPO)":[118],"algorithm.":[119],"We":[120],"demonstrate":[121],"on":[123,139],"real-world":[125],"multiple-objective":[126],"navigation":[127],"problem":[128],"with":[129],"an":[130],"arbitrary":[131],"ordering":[132],"objectives":[134],"both":[135],"simulation":[137],"real":[141],"robot.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}