{"id":"https://openalex.org/W4285145746","doi":"https://doi.org/10.1109/lra.2022.3174258","title":"Developing Cooperative Policies for Multi-Stage Reinforcement Learning Tasks","display_name":"Developing Cooperative Policies for Multi-Stage Reinforcement Learning Tasks","publication_year":2022,"publication_date":"2022-05-11","ids":{"openalex":"https://openalex.org/W4285145746","doi":"https://doi.org/10.1109/lra.2022.3174258"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3174258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3174258","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5054516697","display_name":"Jordan Erskine","orcid":"https://orcid.org/0000-0002-3932-6142"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]},{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Jordan Erskine","raw_affiliation_strings":["Queensland University of Technology, Brisbane, QLD, Australia","Queensland Centre of Robotics, Brisbane, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3932-6142","affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Queensland Centre of Robotics, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I4210127558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081617215","display_name":"Chris Lehnert","orcid":"https://orcid.org/0000-0002-4230-8068"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]},{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christopher Lehnert","raw_affiliation_strings":["Queensland University of Technology, Brisbane, QLD, Australia","Queensland Centre of Robotics, Brisbane, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4230-8068","affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Queensland Centre of Robotics, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I4210127558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054516697"],"corresponding_institution_ids":["https://openalex.org/I160993911","https://openalex.org/I4210127558"],"apc_list":null,"apc_paid":null,"fwci":1.3873,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84150013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":"3","first_page":"6590","last_page":"6597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9775000214576721,"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":0.9775000214576721,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9087691307067871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7623817324638367},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6804818511009216},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5902603268623352},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5863614082336426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5684380531311035},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4508410096168518},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35998088121414185},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09128385782241821},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08017969131469727}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9087691307067871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623817324638367},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6804818511009216},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5902603268623352},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5863614082336426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5684380531311035},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4508410096168518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35998088121414185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09128385782241821},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08017969131469727},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3174258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3174258","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2417280899","https://openalex.org/W2781726626","https://openalex.org/W2964118262","https://openalex.org/W2964227312","https://openalex.org/W3004094900","https://openalex.org/W3213301174","https://openalex.org/W4214717370","https://openalex.org/W6638018090","https://openalex.org/W6730038592","https://openalex.org/W6734215269","https://openalex.org/W6736368053","https://openalex.org/W6738165965","https://openalex.org/W6742667875","https://openalex.org/W6744935223","https://openalex.org/W6747473740","https://openalex.org/W6749821205","https://openalex.org/W6752089545","https://openalex.org/W6752298494","https://openalex.org/W6755069753","https://openalex.org/W6755459604","https://openalex.org/W6757592117","https://openalex.org/W6758134627","https://openalex.org/W6764398561","https://openalex.org/W6764724164","https://openalex.org/W6767317771","https://openalex.org/W6767765287","https://openalex.org/W6769035977","https://openalex.org/W6781678525","https://openalex.org/W6804064799","https://openalex.org/W6841393079"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Many":[0],"hierarchical":[1],"reinforcement":[2],"learning":[3],"algorithms":[4,24],"utilise":[5],"a":[6,12,18,103,108,121,126],"series":[7],"of":[8,21,29,36,47,67,123],"independent":[9],"skills":[10,31],"as":[11,94,96,134,136],"basis":[13],"to":[14,51,70,85,119],"solve":[15,53],"tasks":[16],"at":[17],"higher":[19],"level":[20],"reasoning.":[22],"These":[23],"don\u2019t":[25],"consider":[26],"the":[27,41,65,73,114,131],"value":[28],"using":[30],"that":[32,88],"are":[33,89],"cooperative":[34,115],"instead":[35],"independent.":[37],"This":[38,59],"paper":[39],"proposes":[40],"Cooperative":[42],"Consecutive":[43],"Policies":[44],"(CCP)":[45],"method":[46,60,101],"enabling":[48],"consecutive":[49],"agents":[50],"cooperatively":[52],"long":[54],"time":[55],"horizon":[56],"multi-stage":[57],"tasks.":[58,98],"is":[61],"achieved":[62],"by":[63],"modifying":[64],"policy":[66],"each":[68,83],"agent":[69,84,128],"maximise":[71],"both":[72],"current":[74],"and":[75,107],"next":[76],"agent\u2019s":[77],"critic.":[78],"Cooperatively":[79],"maximising":[80],"critics":[81],"allows":[82],"take":[86],"actions":[87],"beneficial":[90],"for":[91],"its":[92],"task":[93],"well":[95,135],"subsequent":[97],"Using":[99],"this":[100],"in":[102,110],"multi-room":[104],"maze":[105],"domain":[106],"peg":[109],"hole":[111],"manipulation":[112],"domain,":[113,133],"policies":[116],"were":[117],"able":[118],"outperform":[120],"set":[122],"naive":[124],"policies,":[125],"single":[127],"trained":[129],"across":[130],"entire":[132],"another":[137],"sequential":[138],"HRL":[139],"algorithm.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}