{"id":"https://openalex.org/W4206149915","doi":"https://doi.org/10.1109/cog52621.2021.9619068","title":"Hierarchical Advantage for Reinforcement Learning in Parameterized Action Space","display_name":"Hierarchical Advantage for Reinforcement Learning in Parameterized Action Space","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W4206149915","doi":"https://doi.org/10.1109/cog52621.2021.9619068"},"language":"en","primary_location":{"id":"doi:10.1109/cog52621.2021.9619068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9619068","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Games (CoG)","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/A5035718998","display_name":"Zhejie Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I14396692","display_name":"Tokyo University of Information Sciences","ror":"https://ror.org/044bdx604","country_code":"JP","type":"education","lineage":["https://openalex.org/I14396692"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Zhejie Hu","raw_affiliation_strings":["Graduate School of Interdisciplinary Information Studies the University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Interdisciplinary Information Studies the University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103172324","display_name":"Tomoyuki Kaneko","orcid":"https://orcid.org/0000-0001-8051-2388"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyuki Kaneko","raw_affiliation_strings":["Interfaculty Initiative in Information Studies the University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Interfaculty Initiative in Information Studies the University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035718998"],"corresponding_institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.19517667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9553999900817871,"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/T10260","display_name":"Software Engineering Research","score":0.9478999972343445,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/parameterized-complexity","display_name":"Parameterized complexity","score":0.8206262588500977},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8140084743499756},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6580332517623901},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6546638011932373},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5834413766860962},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.539245069026947},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5361518859863281},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.522209107875824},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5220199227333069},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47086918354034424},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.44711488485336304},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22456803917884827},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17190557718276978}],"concepts":[{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.8206262588500977},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8140084743499756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6580332517623901},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6546638011932373},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5834413766860962},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.539245069026947},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5361518859863281},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.522209107875824},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5220199227333069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47086918354034424},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.44711488485336304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22456803917884827},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17190557718276978},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog52621.2021.9619068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9619068","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Games (CoG)","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":32,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W121645403","https://openalex.org/W1191599655","https://openalex.org/W2034587361","https://openalex.org/W2141754131","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2256420211","https://openalex.org/W2257979135","https://openalex.org/W2736601468","https://openalex.org/W2739657930","https://openalex.org/W2781726626","https://openalex.org/W2897417898","https://openalex.org/W2944306386","https://openalex.org/W2949561945","https://openalex.org/W2963257680","https://openalex.org/W2963616477","https://openalex.org/W2963864421","https://openalex.org/W2965757358","https://openalex.org/W3035700320","https://openalex.org/W4243639737","https://openalex.org/W6627932998","https://openalex.org/W6684921986","https://openalex.org/W6691861496","https://openalex.org/W6692312642","https://openalex.org/W6734517396","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6754843927","https://openalex.org/W6755326576","https://openalex.org/W6762592680","https://openalex.org/W6779282036"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W154868527","https://openalex.org/W1494268238","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W1976468483","https://openalex.org/W1516574938","https://openalex.org/W2563912921","https://openalex.org/W2407611282"],"abstract_inverted_index":{"We":[0,66,80],"propose":[1],"a":[2,23,29,63,118],"hierarchical":[3,40,96,108],"architecture":[4,41,45,69,97],"for":[5,52,58],"the":[6,11,43,56,87,95,99,107,113],"advantage":[7,49,100],"function":[8],"to":[9,35,61,77,105,111,117],"improve":[10],"performance":[12],"of":[13,22,25,31,83,98],"reinforcement":[14],"learning":[15,114],"in":[16],"parameterized":[17],"action":[18],"space,":[19],"which":[20,74,102],"consists":[21],"set":[24,30],"discrete":[26,37,53],"actions":[27,54],"and":[28,55,92,115],"continuous":[32,59],"parameters":[33],"corresponding":[34],"each":[36],"action.":[38],"The":[39],"extends":[42],"actor-critic":[44],"with":[46],"two":[47],"specialized":[48],"functions,":[50],"one":[51],"other":[57],"parameters,":[60],"estimate":[62],"better":[64,119],"baseline.":[65],"incorporate":[67],"this":[68],"into":[70],"proximal":[71],"policy":[72],"optimization,":[73],"is":[75,103],"referred":[76,104],"as":[78,106],"HA-PPO.":[79],"evaluated":[81],"all":[82],"our":[84],"methods":[85],"on":[86],"Half":[88],"Field":[89],"Offense":[90],"domain,":[91],"found":[93],"that":[94],"function,":[101],"advantage,":[109],"helps":[110],"stabilize":[112],"leads":[116],"performance.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}