{"id":"https://openalex.org/W4285600554","doi":"https://doi.org/10.24963/ijcai.2022/435","title":"Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems","display_name":"Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285600554","doi":"https://doi.org/10.24963/ijcai.2022/435"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/435","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/435","pdf_url":"https://www.ijcai.org/proceedings/2022/0435.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0435.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018133394","display_name":"Rushang Karia","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rushang Karia","raw_affiliation_strings":["Arizona State University","School of Computing and Augmented Intelligence, Arizona State University, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"School of Computing and Augmented Intelligence, Arizona State University, U.S.A","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104084167","display_name":"Siddharth Srivastava","orcid":"https://orcid.org/0009-0009-5667-8287"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Srivastava","raw_affiliation_strings":["Arizona State University","School of Computing and Augmented Intelligence, Arizona State University, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"School of Computing and Augmented Intelligence, Arizona State University, U.S.A","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.6228,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66933475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3135","last_page":"3142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973000288009644,"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":0.9973000288009644,"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/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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":0.9947999715805054,"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":0.7709518671035767},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7247348427772522},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6331936717033386},{"id":"https://openalex.org/keywords/statistical-relational-learning","display_name":"Statistical relational learning","score":0.5886009335517883},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5869814157485962},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5746800899505615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5418897271156311},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.5334104895591736},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.44536933302879333},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4343298375606537},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.42129838466644287},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.19326230883598328},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.08033466339111328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709518671035767},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7247348427772522},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6331936717033386},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.5886009335517883},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5869814157485962},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5746800899505615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5418897271156311},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.5334104895591736},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.44536933302879333},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4343298375606537},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.42129838466644287},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.19326230883598328},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.08033466339111328},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/435","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/435","pdf_url":"https://www.ijcai.org/proceedings/2022/0435.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/435","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/435","pdf_url":"https://www.ijcai.org/proceedings/2022/0435.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8511392416","display_name":"CAREER: Generalizable and Reliable Behavior Synthesis in Uncertain Open-World Environments","funder_award_id":"1942856","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309835","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285600554.pdf","grobid_xml":"https://content.openalex.org/works/W4285600554.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W129796485","https://openalex.org/W1522301498","https://openalex.org/W1598511582","https://openalex.org/W1967346767","https://openalex.org/W2096149397","https://openalex.org/W2096600060","https://openalex.org/W2111384628","https://openalex.org/W2132096648","https://openalex.org/W2134153324","https://openalex.org/W2150821861","https://openalex.org/W2169173532","https://openalex.org/W2209959171","https://openalex.org/W2210368431","https://openalex.org/W2221305234","https://openalex.org/W2521833123","https://openalex.org/W2621262673","https://openalex.org/W2962730572","https://openalex.org/W2963548923","https://openalex.org/W2964138387","https://openalex.org/W3011120880","https://openalex.org/W3038039195","https://openalex.org/W3042392651","https://openalex.org/W3088458919","https://openalex.org/W3134841710","https://openalex.org/W3175128928","https://openalex.org/W3175830949","https://openalex.org/W3199060092","https://openalex.org/W4214717370","https://openalex.org/W4244275182","https://openalex.org/W4285600554","https://openalex.org/W4287866775","https://openalex.org/W4289232706","https://openalex.org/W4295312788","https://openalex.org/W4297336669","https://openalex.org/W4298857966","https://openalex.org/W4300799055"],"related_works":["https://openalex.org/W1573992054","https://openalex.org/W1599690842","https://openalex.org/W2753053412","https://openalex.org/W2665157442","https://openalex.org/W3108840034","https://openalex.org/W4388169484","https://openalex.org/W2363259562","https://openalex.org/W3036937347","https://openalex.org/W3149224203","https://openalex.org/W98006832"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,33],"in":[2,29],"problems":[3,51,81,93],"with":[4,31],"symbolic":[5],"state":[6,64],"spaces":[7],"is":[8],"challenging":[9],"due":[10],"to":[11,34,49,79,105],"the":[12,69],"need":[13],"for":[14,39,76],"reasoning":[15],"over":[16],"long":[17],"horizons.":[18],"This":[19],"paper":[20],"presents":[21],"a":[22,36,90],"new":[23],"approach":[24],"that":[25,52,68,95],"utilizes":[26],"relational":[27],"abstractions":[28],"conjunction":[30],"deep":[32],"learn":[35],"generalizable":[37],"Q-function":[38,44,72],"such":[40],"problems.":[41],"The":[42],"learned":[43,103],"can":[45,73],"be":[46,74],"efficiently":[47],"transferred":[48],"related":[50,80],"have":[53],"different":[54,63],"object":[55,58],"names":[56],"and":[57,60],"quantities,":[59],"thus,":[61],"entirely":[62],"spaces.":[65],"We":[66],"show":[67,94],"learned,":[70],"generalized":[71],"utilized":[75],"zero-shot":[77,100],"transfer":[78,101],"without":[82],"an":[83],"explicit,":[84],"hand-coded":[85],"curriculum.":[86],"Empirical":[87],"evaluations":[88],"on":[89],"range":[91],"of":[92,102],"our":[96],"method":[97],"facilitates":[98],"efficient":[99],"knowledge":[104],"much":[106],"larger":[107],"problem":[108],"instances":[109],"containing":[110],"many":[111],"objects.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}