{"id":"https://openalex.org/W2889732123","doi":"https://doi.org/10.1609/aaai.v33i01.33013582","title":"Combined Reinforcement Learning via Abstract Representations","display_name":"Combined Reinforcement Learning via Abstract Representations","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2889732123","doi":"https://doi.org/10.1609/aaai.v33i01.33013582","mag":"2889732123"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33013582","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013582","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4238/4116","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4238/4116","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015166903","display_name":"Vincent Fran\u00e7ois-Lavet","orcid":"https://orcid.org/0000-0002-8593-9740"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vincent Francois-Lavet","raw_affiliation_strings":["McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["Universite de Montreal","Universit\u00e8 de Montreal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite de Montreal","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"Universit\u00e8 de Montreal","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065836447","display_name":"Doina Precup","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Doina Precup","raw_affiliation_strings":["McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080591144","display_name":"Jo\u00eblle Pineau","orcid":"https://orcid.org/0000-0003-0747-7250"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joelle Pineau","raw_affiliation_strings":["McGill Unversity"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill Unversity","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0775,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.90681365,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"33","issue":"01","first_page":"3582","last_page":"3589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9937000274658203,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9927999973297119,"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":0.8439739942550659},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7566887140274048},{"id":"https://openalex.org/keywords/modularity","display_name":"Modularity (biology)","score":0.6756707429885864},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6072322130203247},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5919904708862305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5519874095916748},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5182997584342957},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4297105073928833},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3820176124572754},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36723971366882324},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07689866423606873}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8439739942550659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566887140274048},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.6756707429885864},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6072322130203247},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5919904708862305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5519874095916748},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5182997584342957},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4297105073928833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3820176124572754},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36723971366882324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07689866423606873},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v33i01.33013582","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013582","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4238/4116","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1809.04506","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.04506","pdf_url":"https://arxiv.org/pdf/1809.04506","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},{"id":"mag:2889732123","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1809.04506","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.1809.04506","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.04506","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33013582","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013582","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4238/4116","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2889732123.pdf","grobid_xml":"https://content.openalex.org/works/W2889732123.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2076337359","https://openalex.org/W2099471712","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2187089797","https://openalex.org/W2258731934","https://openalex.org/W2260756217","https://openalex.org/W2271840356","https://openalex.org/W2514813345","https://openalex.org/W2523728418","https://openalex.org/W2567374473","https://openalex.org/W2624780181","https://openalex.org/W2735347808","https://openalex.org/W2739083961","https://openalex.org/W2739473244","https://openalex.org/W2759710969","https://openalex.org/W2761873684","https://openalex.org/W2783047733","https://openalex.org/W2799245749","https://openalex.org/W2950872548","https://openalex.org/W2963423916","https://openalex.org/W2964043796","https://openalex.org/W6669402789","https://openalex.org/W6692405165","https://openalex.org/W6727349600","https://openalex.org/W6740836278"],"related_works":["https://openalex.org/W2963488340","https://openalex.org/W2795908317","https://openalex.org/W3110876951","https://openalex.org/W3092318615","https://openalex.org/W2145339207","https://openalex.org/W3206195449","https://openalex.org/W2751395938","https://openalex.org/W2786019934","https://openalex.org/W2199825521","https://openalex.org/W3202251623","https://openalex.org/W3003712948","https://openalex.org/W3016041222","https://openalex.org/W2756350131","https://openalex.org/W2949876402","https://openalex.org/W2739691807","https://openalex.org/W2921528247","https://openalex.org/W2811111819","https://openalex.org/W2888816922","https://openalex.org/W79963452","https://openalex.org/W2159136633"],"abstract_inverted_index":{"In":[0,17,70],"the":[1,37,47,80],"quest":[2],"for":[3,87],"efficient":[4],"and":[5,12,91],"robust":[6],"reinforcement":[7],"learning":[8],"methods,":[9],"both":[10,28],"model-free":[11],"model-based":[13],"approaches":[14,29],"offer":[15],"advantages.":[16],"this":[18,51,72],"paper":[19],"we":[20],"propose":[21],"a":[22,31,65,75],"new":[23,85],"way":[24],"of":[25,36,79],"explicitly":[26],"bridging":[27],"via":[30],"shared":[32],"low-dimensional":[33,77],"learned":[34],"encoding":[35],"environment,":[38,81],"meant":[39],"to":[40,54],"capture":[41],"summarizing":[42],"abstractions.":[43],"We":[44],"show":[45],"that":[46],"modularity":[48],"brought":[49],"by":[50],"approach":[52,73],"leads":[53],"good":[55],"generalization":[56],"while":[57],"being":[58],"computationally":[59],"efficient,":[60],"with":[61],"planning":[62],"happening":[63],"in":[64],"smaller":[66],"latent":[67],"state":[68],"space.":[69],"addition,":[71],"recovers":[74],"sufficient":[76],"representation":[78],"which":[82],"opens":[83],"up":[84],"strategies":[86],"interpretable":[88],"AI,":[89],"exploration":[90],"transfer":[92],"learning.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}