{"id":"https://openalex.org/W1527284173","doi":"https://doi.org/10.1109/robot.2003.1241758","title":"A new approach for structural credit assignment in distributed reinforcement learning systems","display_name":"A new approach for structural credit assignment in distributed reinforcement learning systems","publication_year":2004,"publication_date":"2004-03-02","ids":{"openalex":"https://openalex.org/W1527284173","doi":"https://doi.org/10.1109/robot.2003.1241758","mag":"1527284173"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2003.1241758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2003.1241758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100519440","display_name":"Yu Zhong","orcid":"https://orcid.org/0009-0005-5723-2894"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Yu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Engineering University, Harbin City, Heilongjiang Province, P.R.China","School of Computer Science and Technology, Harbin Engineering of Technology, Harbin, Heilongjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Engineering University, Harbin City, Heilongjiang Province, P.R.China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Engineering of Technology, Harbin, Heilongjiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111610956","display_name":"Guochang Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gu Guochang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Engineering University, Harbin City, Heilongjiang Province, P.R.China","School of Computer Science and Technology, Harbin Engineering of Technology, Harbin, Heilongjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Engineering University, Harbin City, Heilongjiang Province, P.R.China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Engineering of Technology, Harbin, Heilongjiang, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhang Rubo","orcid":null},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Rubo","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Engineering University, Harbin City, Heilongjiang Province, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Engineering University, Harbin City, Heilongjiang Province, P.R.China","institution_ids":["https://openalex.org/I151727225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151727225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"1215","last_page":"1220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9824000000953674,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.944392740726471},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.7362655997276306},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6906642317771912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49154505133628845},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.48067912459373474},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15683671832084656}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.944392740726471},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.7362655997276306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6906642317771912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49154505133628845},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.48067912459373474},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15683671832084656},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robot.2003.1241758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2003.1241758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1513468570","https://openalex.org/W1569296262","https://openalex.org/W1589018387","https://openalex.org/W1665519774","https://openalex.org/W1760997490","https://openalex.org/W2089369806","https://openalex.org/W2105695492","https://openalex.org/W2113102527","https://openalex.org/W2132749700","https://openalex.org/W2141149254","https://openalex.org/W6630520071","https://openalex.org/W6634103402","https://openalex.org/W6635146043"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915","https://openalex.org/W2089415692"],"abstract_inverted_index":{"Most":[0],"existing":[1],"algorithm":[2,110],"for":[3,9],"structural":[4,36,93],"credit":[5,37,45,94],"assignment":[6,38,46,95,116],"are":[7,20,54],"developed":[8],"competitive":[10,15],"reinforcement":[11,16,50,63,72,99],"learning":[12,17,51,100],"systems.":[13],"In":[14,48,84],"system,":[18],"agents":[19,53],"activated":[21,55],"one":[22,29],"by":[23,42],"one,":[24],"so":[25,57],"there":[26],"is":[27,74,102,118],"only":[28],"active":[30],"agent":[31],"at":[32],"a":[33,71,75],"time":[34],"and":[35,91,114],"could":[39,79],"be":[40,81],"implemented":[41],"some":[43],"temporal":[44],"algorithms.":[47],"collaborated":[49,98],"systems,":[52],"simultaneously,":[56],"how":[58],"to":[59,70],"transform":[60],"the":[61,68,87,109,115],"global":[62],"signal":[64],"fed":[65],"back":[66],"from":[67],"environment":[69],"vector":[73],"crucial":[76],"difficulty":[77,96],"that":[78,108],"not":[80],"slide":[82],"over.":[83],"this":[85],"article,":[86],"first":[88],"really":[89],"feasible":[90],"efficient":[92],"in":[97],"systems":[101],"primarily":[103],"solved.":[104],"The":[105],"experiments":[106],"show":[107],"converges":[111],"very":[112],"rapidly":[113],"result":[117],"quite":[119],"satisfying.":[120]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}