{"id":"https://openalex.org/W2794958591","doi":"https://doi.org/10.1109/iros.2018.8594242","title":"Accelerating Learning in Constructive Predictive Frameworks with the Successor Representation","display_name":"Accelerating Learning in Constructive Predictive Frameworks with the Successor Representation","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2794958591","doi":"https://doi.org/10.1109/iros.2018.8594242","mag":"2794958591"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8594242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.09001","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013939722","display_name":"Craig Sherstan","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Craig Sherstan","raw_affiliation_strings":["University of Alberta, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085413987","display_name":"Marlos C. Machado","orcid":"https://orcid.org/0000-0002-0117-6134"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Marlos C. Machado","raw_affiliation_strings":["University of Alberta, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058237113","display_name":"Patrick M. Pilarski","orcid":"https://orcid.org/0000-0003-1686-2978"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Patrick M. Pilarski","raw_affiliation_strings":["University of Alberta, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013939722"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.79424984,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75784931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1212","issue":null,"first_page":"2997","last_page":"3003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9919000267982483,"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":0.9919000267982483,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9909999966621399,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9897000193595886,"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/computer-science","display_name":"Computer science","score":0.7621252536773682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7048541903495789},{"id":"https://openalex.org/keywords/constructive","display_name":"Constructive","score":0.6808087825775146},{"id":"https://openalex.org/keywords/successor-cardinal","display_name":"Successor cardinal","score":0.6306498050689697},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6216232180595398},{"id":"https://openalex.org/keywords/interdependence","display_name":"Interdependence","score":0.5891649723052979},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5836337804794312},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5606919527053833},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5520947575569153},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.549569308757782},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5243157148361206},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4941001236438751},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4746216833591461},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4368411600589752},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08774471282958984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7621252536773682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7048541903495789},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.6808087825775146},{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.6306498050689697},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6216232180595398},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.5891649723052979},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5836337804794312},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5606919527053833},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5520947575569153},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.549569308757782},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5243157148361206},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4941001236438751},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4746216833591461},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4368411600589752},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08774471282958984},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros.2018.8594242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.09001","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.09001","pdf_url":"https://arxiv.org/pdf/1803.09001","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":"mag:2794958591","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1803.09001.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1803.09001","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.09001","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.09001","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.09001","pdf_url":"https://arxiv.org/pdf/1803.09001","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":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2794958591.pdf","grobid_xml":"https://content.openalex.org/works/W2794958591.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1668224097","https://openalex.org/W1981110271","https://openalex.org/W2056354534","https://openalex.org/W2097267906","https://openalex.org/W2101524054","https://openalex.org/W2145339207","https://openalex.org/W2159752377","https://openalex.org/W2766447205","https://openalex.org/W2963019567","https://openalex.org/W2963241009","https://openalex.org/W2963447367","https://openalex.org/W3041202696","https://openalex.org/W4214717370","https://openalex.org/W4231832368","https://openalex.org/W4288598445","https://openalex.org/W6616173779","https://openalex.org/W6679365036","https://openalex.org/W6683583385","https://openalex.org/W6684027447","https://openalex.org/W6729556111","https://openalex.org/W6745277162","https://openalex.org/W6752187413"],"related_works":["https://openalex.org/W2962875084","https://openalex.org/W2785865124","https://openalex.org/W2999490157","https://openalex.org/W2199825521","https://openalex.org/W3095548673","https://openalex.org/W3166838496","https://openalex.org/W3151079898","https://openalex.org/W189652262","https://openalex.org/W2806695138","https://openalex.org/W2952119571","https://openalex.org/W2902253437","https://openalex.org/W3084024636","https://openalex.org/W2475318534","https://openalex.org/W3201617237","https://openalex.org/W3043612295","https://openalex.org/W2999255011","https://openalex.org/W3087873943","https://openalex.org/W2513373085","https://openalex.org/W2786019934","https://openalex.org/W3082248862"],"abstract_inverted_index":{"Here":[0],"we":[1,176],"propose":[2],"using":[3,179],"the":[4,80,91,132,149,152,155],"successor":[5],"representation":[6],"(SR)":[7],"to":[8,35,49,63,98,119],"accelerate":[9],"learning":[10,60,84,133,187,192],"in":[11,65,189,208],"a":[12,41,87,102,145,170,190,209,219],"constructive":[13],"knowledge":[14,136],"system":[15,42],"based":[16],"on":[17,216],"general":[18],"value":[19],"functions":[20],"(GVFs).":[21],"In":[22],"real-world":[23],"settings":[24],"like":[25],"robotics":[26],"for":[27],"unstructured":[28],"and":[29,43,52,61,68,107,158,186,200,211],"dynamic":[30],"environments,":[31],"it":[32],"is":[33,117],"infeasible":[34],"model":[36],"all":[37],"meaningful":[38],"aspects":[39],"of":[40,59,82,89,105,147,151,173],"its":[44,214],"environment":[45,67],"by":[46],"hand":[47],"due":[48],"both":[50],"complexity":[51],"size.":[53],"Instead,":[54],"robots":[55],"must":[56],"be":[57,127,164],"capable":[58],"adapting":[62],"changes":[64],"their":[66,74],"task,":[69],"incrementally":[70,112,123,198],"constructing":[71],"models":[72,100],"from":[73,79,138,154,218],"own":[75],"experience.":[76,140],"GVFs,":[77,109],"taken":[78],"field":[81],"reinforcement":[83],"(RL),":[85],"are":[86,111,197],"way":[88],"modeling":[90],"world":[92,153],"as":[93],"predictive":[94],"questions.":[95],"One":[96],"approach":[97,207],"such":[99,144],"proposes":[101],"massive":[103],"network":[104],"interconnected":[106],"interdependent":[108],"which":[110],"added":[113,124,199],"over":[114,202],"time.":[115,203],"It":[116],"reasonable":[118],"expect":[120],"that":[121,162,178],"new,":[122],"predictions":[125,181,196],"can":[126,163,182],"learned":[128,201],"more":[129],"swiftly":[130],"if":[131],"process":[134],"leverages":[135],"gained":[137],"past":[139],"The":[141],"SR":[142],"provides":[143],"means":[146],"separating":[148],"dynamics":[150],"prediction":[156],"targets":[157],"thus":[159],"capturing":[160],"regularities":[161],"reused":[165],"across":[166],"multiple":[167],"GVFs.":[168],"As":[169],"primary":[171],"contribution":[172],"this":[174],"work,":[175],"show":[177],"SR-based":[180],"improve":[183],"sample":[184],"efficiency":[185],"speed":[188],"continual":[191],"setting":[193],"where":[194],"new":[195],"We":[204],"analyze":[205],"our":[206],"grid-world":[210],"then":[212],"demonstrate":[213],"potential":[215],"data":[217],"physical":[220],"robot":[221],"arm.":[222]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}