{"id":"https://openalex.org/W2156621030","doi":"https://doi.org/10.1109/cit.2008.4594682","title":"Learn adaptive dynamic policy under mixed multi-agent environment","display_name":"Learn adaptive dynamic policy under mixed multi-agent environment","publication_year":2008,"publication_date":"2008-07-01","ids":{"openalex":"https://openalex.org/W2156621030","doi":"https://doi.org/10.1109/cit.2008.4594682","mag":"2156621030"},"language":"en","primary_location":{"id":"doi:10.1109/cit.2008.4594682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cit.2008.4594682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 8th IEEE International Conference on Computer and Information Technology","raw_type":"proceedings-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/A5115597370","display_name":"Zheng Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Xiao","raw_affiliation_strings":["Department of Computing Information Technology, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Information Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100622169","display_name":"Shiyong Zhang","orcid":"https://orcid.org/0000-0002-7255-9204"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyong Zhang","raw_affiliation_strings":["Department of Computing Information Technology, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Information Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11702611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":null,"first_page":"249","last_page":"254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11031","display_name":"Game Theory and Applications","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7468230128288269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7325340509414673},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6772576570510864},{"id":"https://openalex.org/keywords/adaptive-learning","display_name":"Adaptive learning","score":0.5293501019477844},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4644119441509247},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.42173346877098083},{"id":"https://openalex.org/keywords/adaptive-strategies","display_name":"Adaptive strategies","score":0.41738027334213257},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.41275206208229065},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39391472935676575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33248966932296753},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23452097177505493},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13970670104026794},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07551458477973938}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7468230128288269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7325340509414673},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6772576570510864},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.5293501019477844},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4644119441509247},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.42173346877098083},{"id":"https://openalex.org/C167393769","wikidata":"https://www.wikidata.org/wiki/Q4680768","display_name":"Adaptive strategies","level":2,"score":0.41738027334213257},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.41275206208229065},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39391472935676575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33248966932296753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23452097177505493},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13970670104026794},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07551458477973938},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cit.2008.4594682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cit.2008.4594682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 8th IEEE International Conference on Computer and Information Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1513468570","https://openalex.org/W1542941925","https://openalex.org/W1607392272","https://openalex.org/W1972349721","https://openalex.org/W2047918528","https://openalex.org/W2097498347","https://openalex.org/W2120327309","https://openalex.org/W2164637474","https://openalex.org/W6630520071","https://openalex.org/W6636288269","https://openalex.org/W6684470913"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370"],"abstract_inverted_index":{"Equilibrium":[0],"based":[1],"approach":[2],"to":[3,22,61,73,82],"multi-agent":[4],"policy":[5,34,65],"learning":[6,27,90],"supposes":[7],"that":[8,105],"all":[9],"agent":[10],"uses":[11],"the":[12,89],"same":[13],"algorithm.":[14],"Otherwise":[15],"it":[16,39,102],"is":[17,40,103],"easy":[18],"for":[19],"other":[20,44],"agents":[21,106],"exploit":[23],"its":[24],"policy.":[25,95],"Adaptive":[26],"fits":[28],"well":[29,120],"versus":[30],"fixed":[31],"or":[32],"equilibrium":[33],"and":[35,118],"in":[36,121],"self-play.":[37],"But":[38],"deficient":[41],"when":[42],"against":[43,114],"kinds":[45],"of":[46,51,71,75,77],"adaptive":[47,116],"players.":[48],"On":[49],"account":[50],"this":[52,55,108],"mixed":[53],"environment,":[54],"paper":[56],"proposes":[57],"a":[58,85],"novel":[59],"algorithm":[60,109],"learn":[62],"time":[63,83],"dependent":[64],"which":[66,92],"can":[67,110],"also":[68],"be":[69],"capable":[70],"adapting":[72],"dynamics":[74],"policies":[76],"others.":[78],"Policy":[79],"planning":[80],"related":[81],"makes":[84],"key":[86],"difference":[87],"from":[88],"before":[91],"produces":[93],"stationary":[94],"Based":[96],"on":[97],"two":[98],"well-known":[99],"zero-sum":[100],"games":[101],"demonstrated":[104],"using":[107],"get":[111],"higher":[112],"utility":[113],"some":[115],"players,":[117],"perform":[119],"self":[122],"play.":[123]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}