{"id":"https://openalex.org/W3172655270","doi":"https://doi.org/10.1109/icme51207.2021.9428293","title":"Wide-Sense Stationary Policy Optimization with Bellman Residual on Video Games","display_name":"Wide-Sense Stationary Policy Optimization with Bellman Residual on Video Games","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3172655270","doi":"https://doi.org/10.1109/icme51207.2021.9428293","mag":"3172655270"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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/A5045305534","display_name":"Chen Gong","orcid":"https://orcid.org/0000-0001-6178-4118"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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":"Chen Gong","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation","University of Chinese Academy of Sciences, School of Artificial Intelligence","Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734678","display_name":"Qiang He","orcid":"https://orcid.org/0000-0003-0014-1586"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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":"Qiang He","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation","University of Chinese Academy of Sciences, School of Artificial Intelligence","Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064488664","display_name":"Yunpeng Bai","orcid":"https://orcid.org/0000-0001-5670-7230"},"institutions":[{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunpeng Bai","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation","Institute of Automation, Chinese Academy of Sciences","University of Chinese Academy of Sciences, School of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010013507","display_name":"Xinwen Hou","orcid":"https://orcid.org/0000-0002-8468-001X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinwen Hou","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation","Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101572310","display_name":"Guoliang Fan","orcid":"https://orcid.org/0000-0003-2724-2432"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Fan","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation","Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100345672","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0001-9107-6390"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation","Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5045305534"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7205384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"70","issue":null,"first_page":"1","last_page":"6"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9945999979972839,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/residual","display_name":"Residual","score":0.7217194437980652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7147771716117859},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7023199200630188},{"id":"https://openalex.org/keywords/quantile","display_name":"Quantile","score":0.5683018565177917},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5611696839332581},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5195001363754272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46857643127441406},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2951366901397705},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20512154698371887},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10456308722496033}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7217194437980652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147771716117859},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7023199200630188},{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.5683018565177917},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5611696839332581},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5195001363754272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46857643127441406},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2951366901397705},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20512154698371887},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10456308722496033},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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":36,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2017957151","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2724169821","https://openalex.org/W2736601468","https://openalex.org/W2739748921","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2765302304","https://openalex.org/W2787938642","https://openalex.org/W2904675649","https://openalex.org/W2950614095","https://openalex.org/W2951799221","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2982316857","https://openalex.org/W3034359401","https://openalex.org/W3100857200","https://openalex.org/W4214717370","https://openalex.org/W4297797010","https://openalex.org/W4298876402","https://openalex.org/W4302570325","https://openalex.org/W4303494752","https://openalex.org/W6638018090","https://openalex.org/W6683300800","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6740092555","https://openalex.org/W6741002519","https://openalex.org/W6748638692","https://openalex.org/W6748839928","https://openalex.org/W6752089545","https://openalex.org/W6787582224"],"related_works":["https://openalex.org/W1488761988","https://openalex.org/W2044551864","https://openalex.org/W1572557500","https://openalex.org/W3124946120","https://openalex.org/W4390690393","https://openalex.org/W2047938026","https://openalex.org/W2585269888","https://openalex.org/W3132003399","https://openalex.org/W4293365552","https://openalex.org/W2005776175"],"abstract_inverted_index":{"Deep":[0,101],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"has":[4],"an":[5],"increasing":[6],"application":[7],"in":[8],"video":[9,113],"games.":[10],"However,":[11],"it":[12],"usually":[13],"suffers":[14],"from":[15,53],"unstable":[16],"training,":[17],"low":[18],"sampling":[19,72],"efficiency,":[20],"etc.":[21],"Under":[22],"the":[23,34,41,50,54,66,71,76,83,125],"assumption":[24],"that":[25,120],"Bellman":[26,55],"residual":[27],"follows":[28],"a":[29],"stationary":[30],"random":[31],"process":[32,36],"when":[33],"training":[35,67],"is":[37,88],"convergent,":[38],"we":[39,92,128],"propose":[40],"Wide-sense":[42],"Stationary":[43],"Policy":[44,103],"Optimization":[45],"(WSPO)":[46],"framework,":[47],"which":[48],"leverages":[49],"Wasserstein":[51,77],"distance":[52,78],"Residual":[56],"Distribution":[57],"(BRD)":[58],"between":[59],"two":[60],"adjacent":[61],"time":[62],"steps,":[63],"to":[64],"stabilize":[65],"stage":[68],"and":[69,100,115],"improve":[70],"efficiency.":[73],"We":[74,107],"minimize":[75],"with":[79,95],"Quantile":[80],"Regression,":[81],"where":[82],"specific":[84],"form":[85],"of":[86],"BRD":[87],"not":[89],"needed.":[90],"Finally,":[91],"combine":[93],"WSPO":[94,109,121],"Advantage":[96],"Actor-Critic":[97],"(A2C)":[98],"algorithm":[99],"Deterministic":[102],"Gradient":[104],"(DDPG)":[105],"algorithm.":[106],"evaluate":[108],"on":[110],"Atari":[111],"2600":[112],"games":[114],"continuous":[116],"control":[117],"tasks,":[118],"illustrating":[119],"compares":[122],"or":[123],"outperforms":[124],"state-of-the-art":[126],"algorithms":[127],"tested.":[129]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}