{"id":"https://openalex.org/W2963281545","doi":"https://doi.org/10.24963/ijcai.2018/699","title":"Policy Optimization with Second-Order Advantage Information","display_name":"Policy Optimization with Second-Order Advantage Information","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2963281545","doi":"https://doi.org/10.24963/ijcai.2018/699","mag":"2963281545"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/699","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/699","pdf_url":"https://www.ijcai.org/proceedings/2018/0699.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0699.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100708714","display_name":"Jiajin Li","orcid":"https://orcid.org/0000-0001-5299-4447"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiajin Li","raw_affiliation_strings":["The Chinese University of Hong Kong","Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101781010","display_name":"Baoxiang Wang","orcid":"https://orcid.org/0000-0002-6569-9049"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Baoxiang Wang","raw_affiliation_strings":["The Chinese University of Hong Kong","Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shengyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Shengyu Zhang","raw_affiliation_strings":["Tencent","The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.23618419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5038","last_page":"5044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9925000071525574,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9925000071525574,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9919000267982483,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9850000143051147,"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/subspace-topology","display_name":"Subspace topology","score":0.7950186729431152},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6856374740600586},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6463690996170044},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5515350699424744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5485457181930542},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49536263942718506},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.48309755325317383},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43610531091690063},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4360588788986206},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38436341285705566},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3370871841907501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30160507559776306},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1931835114955902}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7950186729431152},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6856374740600586},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6463690996170044},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5515350699424744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5485457181930542},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49536263942718506},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48309755325317383},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43610531091690063},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4360588788986206},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38436341285705566},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3370871841907501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30160507559776306},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1931835114955902},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2018/699","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/699","pdf_url":"https://www.ijcai.org/proceedings/2018/0699.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"mag:2963281545","is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=HkQdaV1vf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/699","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/699","pdf_url":"https://www.ijcai.org/proceedings/2018/0699.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963281545.pdf","grobid_xml":"https://content.openalex.org/works/W2963281545.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2972448932","https://openalex.org/W2918175465","https://openalex.org/W3034214864","https://openalex.org/W2990948232","https://openalex.org/W2950574573","https://openalex.org/W2963923417","https://openalex.org/W3083277700","https://openalex.org/W3037098147","https://openalex.org/W3130565169","https://openalex.org/W2902113407","https://openalex.org/W2997867986","https://openalex.org/W2968953580","https://openalex.org/W2972555185","https://openalex.org/W3198843987","https://openalex.org/W2589171594","https://openalex.org/W2131928195","https://openalex.org/W3011264688","https://openalex.org/W2964218708","https://openalex.org/W2900677334","https://openalex.org/W128438430"],"abstract_inverted_index":{"Policy":[0],"optimization":[1],"on":[2,64,95],"high-dimensional":[3,96],"continuous":[4,103],"control":[5,104],"tasks":[6],"exhibits":[7],"its":[8],"difficulty":[9],"caused":[10],"by":[11,77],"the":[12,16,22,31,45,55,60,65,71,79,92],"large":[13],"variance":[14],"of":[15],"policy":[17],"gradient":[18,26],"estimators.":[19],"We":[20],"present":[21],"action":[23,61],"subspace":[24],"dependent":[25],"(ASDG)":[27],"estimator":[28],"which":[29],"incorporates":[30],"Rao-Blackwell":[32],"theorem":[33],"(RB)":[34],"and":[35,75,99],"Control":[36],"Variates":[37],"(CV)":[38],"into":[39],"a":[40],"unified":[41],"framework":[42],"to":[43],"reduce":[44],"variance.":[46],"To":[47],"invoke":[48],"RB,":[49],"our":[50,88],"proposed":[51,89],"algorithm":[52],"(POSA)":[53],"learns":[54],"underlying":[56],"factorization":[57],"structure":[58],"among":[59],"space":[62],"based":[63],"second-order":[66],"advantage":[67],"information.":[68],"POSA":[69],"captures":[70],"quadratic":[72],"information":[73],"explicitly":[74],"efficiently":[76],"utilizing":[78],"wide":[80],"\\&":[81],"deep":[82],"architecture.":[83],"Empirical":[84],"studies":[85],"show":[86],"that":[87],"approach":[90],"demonstrates":[91],"performance":[93],"improvements":[94],"synthetic":[97],"settings":[98],"OpenAI":[100],"Gym's":[101],"MuJoCo":[102],"tasks.":[105]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}