{"id":"https://openalex.org/W4408613553","doi":"https://doi.org/10.1007/s11424-025-4572-y","title":"On-Policy and Off-Policy Value Iteration Algorithms for Stochastic Zero-Sum Dynamic Games","display_name":"On-Policy and Off-Policy Value Iteration Algorithms for Stochastic Zero-Sum Dynamic Games","publication_year":2025,"publication_date":"2025-02-01","ids":{"openalex":"https://openalex.org/W4408613553","doi":"https://doi.org/10.1007/s11424-025-4572-y"},"language":"en","primary_location":{"id":"doi:10.1007/s11424-025-4572-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11424-025-4572-y","pdf_url":null,"source":{"id":"https://openalex.org/S45848134","display_name":"Journal of Systems Science and Complexity","issn_l":"1009-6124","issn":["1009-6124","1559-7067"],"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":"Journal of Systems Science and Complexity","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/A5080260781","display_name":"Liangyuan Guo","orcid":"https://orcid.org/0009-0009-3590-277X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]},{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangyuan Guo","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, 250063, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, 250063, China","institution_ids":["https://openalex.org/I154099455","https://openalex.org/I34949971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017397385","display_name":"Bing\u2010Chang Wang","orcid":"https://orcid.org/0000-0003-3882-8615"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]},{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bing-Chang Wang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, 250063, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, 250063, China","institution_ids":["https://openalex.org/I154099455","https://openalex.org/I34949971"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100784043","display_name":"Ji\u2010Feng Zhang","orcid":"https://orcid.org/0000-0002-0656-2886"},"institutions":[{"id":"https://openalex.org/I132586189","display_name":"Zhongyuan University of Technology","ror":"https://ror.org/0360zcg91","country_code":"CN","type":"education","lineage":["https://openalex.org/I132586189"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120485","display_name":"Academy of Mathematics and Systems Science","ror":"https://ror.org/02jkmyk67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210120485"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji-Feng Zhang","raw_affiliation_strings":["Key Laboratory of Systems and Control, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, 100190, China","School of Automation and Electrical Engineering, Zhongyuan University of Technology, Zhengzhou, 450007, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Systems and Control, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210120485"]},{"raw_affiliation_string":"School of Automation and Electrical Engineering, Zhongyuan University of Technology, Zhengzhou, 450007, China","institution_ids":["https://openalex.org/I132586189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017397385"],"corresponding_institution_ids":["https://openalex.org/I154099455","https://openalex.org/I34949971"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05500696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"1","first_page":"421","last_page":"435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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/T11886","display_name":"Agricultural risk and resilience","score":0.9593999981880188,"subfield":{"id":"https://openalex.org/subfields/1111","display_name":"Soil Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6881469488143921},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5946811437606812},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5224732160568237},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.45873892307281494},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.4437014162540436},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4354107677936554},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42537933588027954},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40224123001098633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3905158042907715},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3580628037452698},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15103429555892944},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.10639217495918274}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6881469488143921},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5946811437606812},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5224732160568237},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.45873892307281494},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.4437014162540436},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4354107677936554},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42537933588027954},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40224123001098633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3905158042907715},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3580628037452698},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15103429555892944},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.10639217495918274},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11424-025-4572-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11424-025-4572-y","pdf_url":null,"source":{"id":"https://openalex.org/S45848134","display_name":"Journal of Systems Science and Complexity","issn_l":"1009-6124","issn":["1009-6124","1559-7067"],"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":"Journal of Systems Science and Complexity","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W560518094","https://openalex.org/W1977068734","https://openalex.org/W2005437559","https://openalex.org/W2009533501","https://openalex.org/W2024303516","https://openalex.org/W2052399669","https://openalex.org/W2069199044","https://openalex.org/W2093831009","https://openalex.org/W2112103082","https://openalex.org/W2148439597","https://openalex.org/W2151966330","https://openalex.org/W2250513429","https://openalex.org/W2331243380","https://openalex.org/W2570494446","https://openalex.org/W2766502495","https://openalex.org/W2772589676","https://openalex.org/W2807176303","https://openalex.org/W2914054366","https://openalex.org/W2947577977","https://openalex.org/W2995552585","https://openalex.org/W3009014967","https://openalex.org/W3108003339","https://openalex.org/W3114329882","https://openalex.org/W4308902993","https://openalex.org/W4383506070","https://openalex.org/W4393942688","https://openalex.org/W4402052499","https://openalex.org/W4404723206"],"related_works":["https://openalex.org/W4389475841","https://openalex.org/W4241327272","https://openalex.org/W2120406836","https://openalex.org/W1996214847","https://openalex.org/W2903299703","https://openalex.org/W2117282672","https://openalex.org/W4211224558","https://openalex.org/W4281791088","https://openalex.org/W2119790124","https://openalex.org/W4385342861"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
