{"id":"https://openalex.org/W3090890719","doi":"https://doi.org/10.1109/icip40778.2020.9190994","title":"Generalized Critic Policy Optimization: A Model For Combining Advantage Estimates In Actor Critic Methods","display_name":"Generalized Critic Policy Optimization: A Model For Combining Advantage Estimates In Actor Critic Methods","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3090890719","doi":"https://doi.org/10.1109/icip40778.2020.9190994","mag":"3090890719"},"language":"en","primary_location":{"id":"doi:10.1109/icip40778.2020.9190994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","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/A5081160763","display_name":"Roumeissa Kitouni","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Roumeissa Kitouni","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017459581","display_name":"Abderrahim Kitouni","orcid":"https://orcid.org/0000-0002-4474-2263"},"institutions":[{"id":"https://openalex.org/I4391767747","display_name":"University of Constantine 3","ror":"https://ror.org/04wk25q62","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4391767747"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Abderrahim Kitouni","raw_affiliation_strings":["Department of Mathematics, University of Constantine 1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Constantine 1","institution_ids":["https://openalex.org/I4391767747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054864573","display_name":"Feng Jiang","orcid":"https://orcid.org/0000-0001-8342-1211"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Jiang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2708,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6495439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"135","issue":null,"first_page":"3184","last_page":"3188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9480000138282776,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9376999735832214,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7284424304962158},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6346335411071777},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6334584951400757},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5495830178260803},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5480690598487854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5384381413459778},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5337233543395996},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5330981612205505},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5269311666488647},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4988095760345459},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4188289940357208},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35479801893234253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18383190035820007}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7284424304962158},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6346335411071777},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6334584951400757},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5495830178260803},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5480690598487854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5384381413459778},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5337233543395996},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5330981612205505},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5269311666488647},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4988095760345459},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4188289940357208},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35479801893234253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18383190035820007},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip40778.2020.9190994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","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/W1191599655","https://openalex.org/W1515851193","https://openalex.org/W2736601468","https://openalex.org/W2747402019","https://openalex.org/W2754517384","https://openalex.org/W2755012395","https://openalex.org/W2963120839","https://openalex.org/W3037207827","https://openalex.org/W6627932998","https://openalex.org/W6741002519","https://openalex.org/W6742945991"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698","https://openalex.org/W1859185863","https://openalex.org/W2964126589","https://openalex.org/W4285537323","https://openalex.org/W1932159282","https://openalex.org/W4307691181","https://openalex.org/W3016225735"],"abstract_inverted_index":{"We":[0,33,58],"present":[1],"a":[2,19,63],"general":[3],"model":[4],"for":[5],"actor":[6],"critic":[7],"methods":[8],"that":[9],"represent":[10],"the":[11,24,30,35,49,66,69,73,77],"possibility":[12],"of":[13,37,48,68,76],"combining":[14],"value":[15],"function":[16],"estimations":[17],"as":[18],"means":[20],"to":[21,45],"further":[22],"reduce":[23],"policy":[25,78],"gradient\u2019s":[26],"variance":[27],"and":[28],"improve":[29],"learning":[31],"result.":[32],"show":[34,59],"potential":[36],"this":[38],"architecture":[39],"by":[40,60],"implementing":[41],"an":[42],"example":[43],"case":[44,65],"learn":[46],"some":[47],"Pybullet":[50],"continous":[51],"control":[52],"robotic":[53],"tasks":[54],"with":[55,62],"OpenAI":[56],"Gym.":[57],"experimenting":[61],"special":[64],"effect":[67],"external":[70],"parameters":[71],"on":[72],"overall":[74],"performance":[75],"optimization":[79],"algorithm.":[80]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}