{"id":"https://openalex.org/W4389508974","doi":"https://doi.org/10.1007/s10458-023-09630-9","title":"IOB: integrating optimization transfer and behavior transfer for multi-policy reuse","display_name":"IOB: integrating optimization transfer and behavior transfer for multi-policy reuse","publication_year":2023,"publication_date":"2023-12-09","ids":{"openalex":"https://openalex.org/W4389508974","doi":"https://doi.org/10.1007/s10458-023-09630-9"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-023-09630-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-023-09630-9","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"type":"article","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/A5100406638","display_name":"Siyuan Li","orcid":"https://orcid.org/0000-0002-9999-437X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Li","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, 150001, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, 150001, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348617","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-6294-6761"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["School of Cybersecurity, Northwestern Polytechnical University, 710072, Xi\u2019an, China","School of Cybersecurity, Northwestern Polytechnical University, 710072, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, 710072, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, 710072, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406005","display_name":"Jin Zhang","orcid":"https://orcid.org/0000-0003-0717-8437"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Zhang","raw_affiliation_strings":["Interdisciplinary Information Sciences, Tsinghua University, 100084, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Information Sciences, Tsinghua University, 100084, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422377","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-8182-2852"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["School of Cybersecurity, Northwestern Polytechnical University, 710072, Xi\u2019an, China","School of Cybersecurity, Northwestern Polytechnical University, 710072, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, 710072, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, 710072, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346747","display_name":"Peng Liu","orcid":"https://orcid.org/0000-0001-6568-1335"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, 150001, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, 150001, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010176958","display_name":"Chongjie Zhang","orcid":"https://orcid.org/0000-0001-8068-0162"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chongjie Zhang","raw_affiliation_strings":["McKelvey School of Engineering, Washington University in St. Louis, St. Louis, 63130, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McKelvey School of Engineering, Washington University in St. Louis, St. Louis, 63130, USA","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010176958"],"corresponding_institution_ids":["https://openalex.org/I204465549"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.5637,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73043018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"38","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9735000133514404,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9684000015258789,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7632371187210083},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6776675581932068},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6695773601531982},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6553439497947693},{"id":"https://openalex.org/keywords/policy-transfer","display_name":"Policy transfer","score":0.633885383605957},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4679837226867676},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4666236639022827},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.44471171498298645},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.4421050548553467},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.42541757225990295},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3818683624267578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34165889024734497},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26348578929901123},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.09344780445098877},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09007468819618225},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08220863342285156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7632371187210083},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6776675581932068},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6695773601531982},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6553439497947693},{"id":"https://openalex.org/C2776731479","wikidata":"https://www.wikidata.org/wiki/Q15142682","display_name":"Policy transfer","level":2,"score":0.633885383605957},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4679837226867676},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4666236639022827},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.44471171498298645},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.4421050548553467},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.42541757225990295},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3818683624267578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34165889024734497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26348578929901123},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.09344780445098877},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09007468819618225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08220863342285156},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C3116431","wikidata":"https://www.wikidata.org/wiki/Q31728","display_name":"Public administration","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10458-023-09630-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-023-09630-9","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G875864507","display_name":null,"funder_award_id":"LH2021F023","funder_id":"https://openalex.org/F4320323085","funder_display_name":"Natural Science Foundation of Heilongjiang Province"},{"id":"https://openalex.org/G915215520","display_name":null,"funder_award_id":"62306088","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1575592356","https://openalex.org/W1981276685","https://openalex.org/W2031727428","https://openalex.org/W2039118719","https://openalex.org/W2149306165","https://openalex.org/W2173248099","https://openalex.org/W2440926996","https://openalex.org/W2586101872","https://openalex.org/W2605369401","https://openalex.org/W2760355785","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2804175194","https://openalex.org/W2923504512","https://openalex.org/W2963072899","https://openalex.org/W2971266180","https://openalex.org/W2976782275","https://openalex.org/W2981344907","https://openalex.org/W2982316857","https://openalex.org/W2994987910","https://openalex.org/W3013821552","https://openalex.org/W3021619395","https://openalex.org/W3034724428","https://openalex.org/W3034815680","https://openalex.org/W3035760261","https://openalex.org/W3039459278","https://openalex.org/W3103079199","https://openalex.org/W3128507558","https://openalex.org/W3134939669","https://openalex.org/W3165631200","https://openalex.org/W3167156317","https://openalex.org/W3168892396","https://openalex.org/W6633471584","https://openalex.org/W6740879895","https://openalex.org/W6780404908","https://openalex.org/W6845928926"],"related_works":["https://openalex.org/W2797217915","https://openalex.org/W1973501944","https://openalex.org/W3017796982","https://openalex.org/W2027342354","https://openalex.org/W4390665401","https://openalex.org/W2142370952","https://openalex.org/W3095475970","https://openalex.org/W2035231162","https://openalex.org/W2038408936","https://openalex.org/W2087229268"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
