{"id":"https://openalex.org/W4409877609","doi":"https://doi.org/10.1007/s10489-024-06083-9","title":"Enhancing model learning in reinforcement learning through Q-function-guided trajectory alignment","display_name":"Enhancing model learning in reinforcement learning through Q-function-guided trajectory alignment","publication_year":2025,"publication_date":"2025-04-28","ids":{"openalex":"https://openalex.org/W4409877609","doi":"https://doi.org/10.1007/s10489-024-06083-9"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-024-06083-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-024-06083-9","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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":"Applied Intelligence","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/A5113254439","display_name":"Xin Du","orcid":"https://orcid.org/0009-0006-0308-2664"},"institutions":[{"id":"https://openalex.org/I21741975","display_name":"Changshu Institute of Technology","ror":"https://ror.org/05g6ben79","country_code":"CN","type":"education","lineage":["https://openalex.org/I21741975"]},{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Du","raw_affiliation_strings":["School of Computer Science and Engineering, Changshu Institute of Technology, SuZhou, 215506, JiangSu, China","School of Electronics and Information Engineering, Suzhou University of Science and Technology, SuZhou, 215506, JiangSu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Changshu Institute of Technology, SuZhou, 215506, JiangSu, China","institution_ids":["https://openalex.org/I21741975"]},{"raw_affiliation_string":"School of Electronics and Information Engineering, Suzhou University of Science and Technology, SuZhou, 215506, JiangSu, China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101902909","display_name":"Shan Zhong","orcid":"https://orcid.org/0000-0003-0034-6952"},"institutions":[{"id":"https://openalex.org/I21741975","display_name":"Changshu Institute of Technology","ror":"https://ror.org/05g6ben79","country_code":"CN","type":"education","lineage":["https://openalex.org/I21741975"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Zhong","raw_affiliation_strings":["School of Computer Science and Engineering, Changshu Institute of Technology, SuZhou, 215506, JiangSu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Changshu Institute of Technology, SuZhou, 215506, JiangSu, China","institution_ids":["https://openalex.org/I21741975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038799336","display_name":"Shengrong Gong","orcid":"https://orcid.org/0000-0003-0266-2422"},"institutions":[{"id":"https://openalex.org/I21741975","display_name":"Changshu Institute of Technology","ror":"https://ror.org/05g6ben79","country_code":"CN","type":"education","lineage":["https://openalex.org/I21741975"]},{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengrong Gong","raw_affiliation_strings":["School of Computer Science and Engineering, Changshu Institute of Technology, SuZhou, 215506, JiangSu, China","School of Electronics and Information Engineering, Suzhou University of Science and Technology, SuZhou, 215506, JiangSu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Changshu Institute of Technology, SuZhou, 215506, JiangSu, China","institution_ids":["https://openalex.org/I21741975"]},{"raw_affiliation_string":"School of Electronics and Information Engineering, Suzhou University of Science and Technology, SuZhou, 215506, JiangSu, China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059843859","display_name":"Yali Si","orcid":null},"institutions":[{"id":"https://openalex.org/I21741975","display_name":"Changshu Institute of Technology","ror":"https://ror.org/05g6ben79","country_code":"CN","type":"education","lineage":["https://openalex.org/I21741975"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yali Si","raw_affiliation_strings":["School of Computer Science and Engineering, Changshu Institute of Technology, SuZhou, 215506, JiangSu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Changshu Institute of Technology, SuZhou, 215506, JiangSu, China","institution_ids":["https://openalex.org/I21741975"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068005043","display_name":"Zhenyu Qi","orcid":"https://orcid.org/0009-0000-1108-229X"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenyu Qi","raw_affiliation_strings":["University of Arizona, Tucson, AZ, 85711, USA"],"affiliations":[{"raw_affiliation_string":"University of Arizona, Tucson, AZ, 85711, USA","institution_ids":["https://openalex.org/I138006243"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113254439"],"corresponding_institution_ids":["https://openalex.org/I21741975","https://openalex.org/I308837"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04090789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"55","issue":"10","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":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9951000213623047,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8871258497238159},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8500487804412842},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.648171067237854},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5919206738471985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5148369669914246},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4999809265136719},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3427616357803345},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05579638481140137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8871258497238159},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8500487804412842},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.648171067237854},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5919206738471985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5148369669914246},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4999809265136719},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3427616357803345},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05579638481140137},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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:10.1007/s10489-024-06083-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-024-06083-9","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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":"Applied Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2447216977","display_name":null,"funder_award_id":"62376041","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2593542410","display_name":null,"funder_award_id":"2021M69236","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3768599159","display_name":null,"funder_award_id":"62102347","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G831781406","display_name":null,"funder_award_id":"ZR2023MF0766","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2132083787","https://openalex.org/W2145339207","https://openalex.org/W2153244676","https://openalex.org/W2554684686","https://openalex.org/W2572640103","https://openalex.org/W2962872206","https://openalex.org/W2997933098","https://openalex.org/W3038822267","https://openalex.org/W3195968524","https://openalex.org/W4205942265","https://openalex.org/W4213126473","https://openalex.org/W4226265052","https://openalex.org/W4226345170","https://openalex.org/W4293251159","https://openalex.org/W4318159260","https://openalex.org/W4387031435","https://openalex.org/W4390264450","https://openalex.org/W4391259941","https://openalex.org/W4391325403","https://openalex.org/W6600018615","https://openalex.org/W6600474606","https://openalex.org/W6601211009","https://openalex.org/W6815970816"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2952356279"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
