{"id":"https://openalex.org/W4417152415","doi":"https://doi.org/10.1007/s10489-025-07035-7","title":"Sample-efficient multi-agent reinforcement learning with high update-to-data ratio and state-action embedding","display_name":"Sample-efficient multi-agent reinforcement learning with high update-to-data ratio and state-action embedding","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W4417152415","doi":"https://doi.org/10.1007/s10489-025-07035-7"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-025-07035-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-025-07035-7","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/A5034393588","display_name":"Chenyang Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenyang Miao","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yingzhuo Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingzhuo Jiang","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011048472","display_name":"Yunduan Cui","orcid":"https://orcid.org/0000-0001-5539-4260"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunduan Cui","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-5539-4260","affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100689058","display_name":"Yidong Chen","orcid":"https://orcid.org/0000-0002-0243-7228"},"institutions":[{"id":"https://openalex.org/I4210086346","display_name":"Guangdong Machinery Research Institute","ror":"https://ror.org/000wc3348","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210086346"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidong Chen","raw_affiliation_strings":["Shenzhen ZHAOWEI Machinery & Electronics Co., Ltd., Shenzhen, 518105, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen ZHAOWEI Machinery & Electronics Co., Ltd., Shenzhen, 518105, Guangdong, China","institution_ids":["https://openalex.org/I4210086346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091902960","display_name":"Tianfu Sun","orcid":"https://orcid.org/0000-0002-5518-0315"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianfu Sun","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5034393588"],"corresponding_institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I4210165038"],"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":0.20035395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"55","issue":"18","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":0.5751000046730042,"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":0.5751000046730042,"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":0.33309999108314514,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.009999999776482582,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8537999987602234},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7791000008583069},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5878999829292297},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.527999997138977},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5202000141143799},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4586000144481659},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.3921000063419342},{"id":"https://openalex.org/keywords/relative-value","display_name":"Relative value","score":0.3677000105381012}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8537999987602234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8119999766349792},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7791000008583069},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5878999829292297},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.527999997138977},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5202000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4860000014305115},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.3921000063419342},{"id":"https://openalex.org/C201236551","wikidata":"https://www.wikidata.org/wiki/Q7310809","display_name":"Relative value","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3490999937057495},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33809998631477356},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.33550000190734863},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2694000005722046}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-025-07035-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-025-07035-7","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":[],"awards":[{"id":"https://openalex.org/G517294329","display_name":null,"funder_award_id":"62103403","funder_id":"https://openalex.org/F4320315254","funder_display_name":"Innovative Research Group Project of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2145339207","https://openalex.org/W2902907165","https://openalex.org/W2997070234","https://openalex.org/W2999862950","https://openalex.org/W3004881034","https://openalex.org/W3153787838","https://openalex.org/W3175254947","https://openalex.org/W3175558129","https://openalex.org/W3207924272","https://openalex.org/W4205295909","https://openalex.org/W4379507295"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-12-10T02:49:46.989445","created_date":"2025-12-09T00:00:00"}
