{"id":"https://openalex.org/W4392903915","doi":"https://doi.org/10.1109/icassp48485.2024.10447319","title":"Computational Complexity of Asynchronous Policy Iteration for Two-Player Zero-Sum Markov Games","display_name":"Computational Complexity of Asynchronous Policy Iteration for Two-Player Zero-Sum Markov Games","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903915","doi":"https://doi.org/10.1109/icassp48485.2024.10447319"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101908951","display_name":"Chenyu Xu","orcid":"https://orcid.org/0000-0003-0547-8786"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chenyu Xu","raw_affiliation_strings":["Iowa State University"],"affiliations":[{"raw_affiliation_string":"Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002524087","display_name":"Sihai Zhang","orcid":"https://orcid.org/0000-0001-5758-2169"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sihai Zhang","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009345756","display_name":"Zhengdao Wang","orcid":"https://orcid.org/0000-0003-2491-7879"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengdao Wang","raw_affiliation_strings":["George Mason University"],"affiliations":[{"raw_affiliation_string":"George Mason University","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101908951"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61716573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7580","last_page":"7584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9901000261306763,"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":0.9901000261306763,"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/T12288","display_name":"Optimization and Search Problems","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10142","display_name":"Formal Methods in Verification","score":0.9801999926567078,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.7008855938911438},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5692561864852905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5548765659332275},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4786480665206909},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4618033766746521},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.46072888374328613},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.43047934770584106},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4285874366760254},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.42094194889068604},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3819667398929596},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37441736459732056},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3613817095756531},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10452371835708618},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09512192010879517}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7008855938911438},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5692561864852905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5548765659332275},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4786480665206909},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4618033766746521},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.46072888374328613},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.43047934770584106},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4285874366760254},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42094194889068604},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3819667398929596},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37441736459732056},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3613817095756531},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10452371835708618},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09512192010879517},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W51114640","https://openalex.org/W2028560736","https://openalex.org/W2066538609","https://openalex.org/W2128646067","https://openalex.org/W2130541529","https://openalex.org/W2156268532","https://openalex.org/W2493676419","https://openalex.org/W2574665470","https://openalex.org/W3003257820","https://openalex.org/W3017378904","https://openalex.org/W4254547512","https://openalex.org/W4287070472","https://openalex.org/W4315472236","https://openalex.org/W6776542292","https://openalex.org/W6798935556"],"related_works":["https://openalex.org/W2116677773","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2315999538","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Bertsekas":[0],"recently":[1],"proposed":[2],"Asynchronous":[3],"Policy":[4,12],"Iteration":[5,13],"(API)":[6],"as":[7],"an":[8],"alternative":[9],"algorithm":[10],"of":[11,19,28,40,49,67,93,107],"(PI)":[14],"for":[15,33,109],"solving":[16],"the":[17,26,38,46,60,64,91,105,119],"problem":[18],"two-player":[20],"zero-sum":[21],"Markov":[22],"games.":[23],"To":[24],"quantifying":[25],"benefits":[27],"API,":[29],"besides":[30],"its":[31],"flexibility":[32],"parallel":[34],"and":[35,112,116],"asynchronous":[36],"implementation,":[37],"focus":[39],"this":[41],"paper":[42],"is":[43,69,90,118],"to":[44,54,59],"derive":[45],"computational":[47,65],"complexity":[48,66],"API.":[50],"We":[51],"show":[52],"that":[53],"reach":[55],"within":[56],"\u03f5":[57],"error":[58],"optimal":[61],"value":[62],"function,":[63],"API":[68],"at":[70],"most":[71],"O":[72],"(poly":[73],"(n,":[74],"m":[75,80,95,100],"<inf":[76,81,96,101],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[77,82,97,102],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</inf>":[78,98],",":[79,84,99],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</inf>":[83,103],"ln(1/(1":[85],"\u2212":[86],"\u03b3))),":[87],"where":[88],"n":[89],"number":[92,106],"states,":[94],"are":[104],"actions":[108],"player":[110,113],"1":[111],"2":[114],"respectively,":[115],"\u03b3":[117],"discount":[120],"factor.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}