{"id":"https://openalex.org/W2966387108","doi":"https://doi.org/10.24963/ijcai.2019/273","title":"Unobserved Is Not Equal to Non-existent: Using Gaussian Processes to Infer Immediate Rewards Across Contexts","display_name":"Unobserved Is Not Equal to Non-existent: Using Gaussian Processes to Infer Immediate Rewards Across Contexts","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2966387108","doi":"https://doi.org/10.24963/ijcai.2019/273","mag":"2966387108"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/273","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/273","pdf_url":"https://www.ijcai.org/proceedings/2019/0273.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0273.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027571540","display_name":"Hamoon Azizsoltani","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hamoon Azizsoltani","raw_affiliation_strings":["North Carolina State University"],"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103202565","display_name":"Yeo Jin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yeo Jin Kim","raw_affiliation_strings":["North Carolina State University"],"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039146131","display_name":"Markel Sanz Ausin","orcid":"https://orcid.org/0000-0002-4526-9252"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Markel Sanz Ausin","raw_affiliation_strings":["North Carolina State University"],"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083076004","display_name":"Tiffany Barnes","orcid":"https://orcid.org/0000-0002-6500-9976"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiffany Barnes","raw_affiliation_strings":["North Carolina State University"],"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090231772","display_name":"Min Chi","orcid":"https://orcid.org/0000-0003-1765-7837"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Chi","raw_affiliation_strings":["North Carolina State University"],"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027571540"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":1.9602,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89754856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1974","last_page":"1980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9861999750137329,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9861999750137329,"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/T13283","display_name":"Mental Health Research Topics","score":0.9473000168800354,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9368000030517578,"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":0.8209402561187744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6833394169807434},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.6140331029891968},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5525932312011719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5433358550071716},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5251036882400513},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4655616581439972},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4485741853713989}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8209402561187744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833394169807434},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.6140331029891968},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5525932312011719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5433358550071716},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5251036882400513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4655616581439972},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4485741853713989},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/273","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/273","pdf_url":"https://www.ijcai.org/proceedings/2019/0273.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/273","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/273","pdf_url":"https://www.ijcai.org/proceedings/2019/0273.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2966387108.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1502922572","https://openalex.org/W1777239053","https://openalex.org/W1963697479","https://openalex.org/W1980909828","https://openalex.org/W1999874108","https://openalex.org/W2046109394","https://openalex.org/W2061562262","https://openalex.org/W2064675550","https://openalex.org/W2121863487","https://openalex.org/W2124611503","https://openalex.org/W2132849848","https://openalex.org/W2143022286","https://openalex.org/W2145339207","https://openalex.org/W2151268438","https://openalex.org/W2155968351","https://openalex.org/W2156974606","https://openalex.org/W2161009228","https://openalex.org/W2164419340","https://openalex.org/W2188721763","https://openalex.org/W2201581102","https://openalex.org/W2293184044","https://openalex.org/W2335959470","https://openalex.org/W2746553466","https://openalex.org/W2807748885","https://openalex.org/W2862751544","https://openalex.org/W2884978427","https://openalex.org/W2891236810","https://openalex.org/W2963262099","https://openalex.org/W4236496685","https://openalex.org/W4301178047","https://openalex.org/W4394666657","https://openalex.org/W6620497712","https://openalex.org/W6650265722","https://openalex.org/W6681402394","https://openalex.org/W6682489347","https://openalex.org/W6682897353"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W1964286703","https://openalex.org/W2169866437","https://openalex.org/W4205650496"],"abstract_inverted_index":{"Learning":[0],"optimal":[1],"policies":[2,115,118],"in":[3,13,36,123],"real-world":[4,125],"domains":[5],"with":[6,102],"delayed":[7,43,89,121],"rewards":[8,40,57,101,122],"is":[9],"a":[10,24],"major":[11],"challenge":[12],"Reinforcement":[14],"Learning.":[15],"We":[16],"address":[17],"the":[18,69,80,87,112,117],"credit":[19],"assignment":[20],"problem":[21],"by":[22],"proposing":[23],"Gaussian":[25],"Process":[26],"(GP)-based":[27],"immediate":[28,56,81,100],"reward":[29,72,82,90,114],"approximation":[30],"algorithm":[31],"and":[32,51,84,94,109],"evaluate":[33],"its":[34],"effectiveness":[35],"4":[37],"contexts":[38],"where":[39,55],"can":[41],"be":[42],"for":[44],"long":[45],"trajectories.":[46],"In":[47,92],"one":[48],"GridWorld":[49],"game":[50],"8":[52],"Atari":[53],"games,":[54,68],"are":[58],"available,":[59],"our":[60],"results":[61],"showed":[62,110],"that":[63,111],"on":[64],"7":[65],"out":[66],"9":[67],"proposed":[70],"GP-inferred":[71,99,113],"policy":[73,83,107],"performed":[74],"at":[75],"least":[76],"as":[77,79],"well":[78],"significantly":[85],"outperformed":[86,116],"corresponding":[88],"policy.":[91],"e-learning":[93],"healthcare":[95],"applications,":[96],"we":[97],"combined":[98],"offline":[103],"Deep":[104],"Q-Network":[105],"(DQN)":[106],"induction":[108],"induced":[119],"using":[120],"both":[124],"contexts.":[126]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-01-15T23:16:33.117629","created_date":"2025-10-10T00:00:00"}