{"id":"https://openalex.org/W2134898265","doi":"https://doi.org/10.1109/devlrn.2011.6037351","title":"Scalable reinforcement learning through hierarchical decompositions for weakly-coupled problems","display_name":"Scalable reinforcement learning through hierarchical decompositions for weakly-coupled problems","publication_year":2011,"publication_date":"2011-08-01","ids":{"openalex":"https://openalex.org/W2134898265","doi":"https://doi.org/10.1109/devlrn.2011.6037351","mag":"2134898265"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2011.6037351","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2011.6037351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nottingham-repository.worktribe.com/output/4754330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075009707","display_name":"Hazem Toutounji","orcid":"https://orcid.org/0000-0002-2655-3071"},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]},{"id":"https://openalex.org/I2801628138","display_name":"Frankfurt Institute for Advanced Studies","ror":"https://ror.org/05vmv8m79","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2801628138"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hazem Toutounji","raw_affiliation_strings":["Frankfurt Institute for Advanced Studies, Germany","Frankfurt Institute for Advanced Studies, Frankfurt, Germany","Institute of Cognitive Science, University of Osnabrueck, Osnabrueck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Frankfurt Institute for Advanced Studies, Germany","institution_ids":["https://openalex.org/I2801628138"]},{"raw_affiliation_string":"Frankfurt Institute for Advanced Studies, Frankfurt, Germany","institution_ids":["https://openalex.org/I2801628138"]},{"raw_affiliation_string":"Institute of Cognitive Science, University of Osnabrueck, Osnabrueck, Germany","institution_ids":["https://openalex.org/I170658231"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015277967","display_name":"Constantin A. Rothkopf","orcid":"https://orcid.org/0000-0002-5636-0801"},"institutions":[{"id":"https://openalex.org/I2801628138","display_name":"Frankfurt Institute for Advanced Studies","ror":"https://ror.org/05vmv8m79","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2801628138"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Constantin A. Rothkopf","raw_affiliation_strings":["Frankfurt Institute for Advanced Studies, Germany","Frankfurt Institute for Advanced Studies, Frankfurt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Frankfurt Institute for Advanced Studies, Germany","institution_ids":["https://openalex.org/I2801628138"]},{"raw_affiliation_string":"Frankfurt Institute for Advanced Studies, Frankfurt, Germany","institution_ids":["https://openalex.org/I2801628138"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065703786","display_name":"Jochen Triesch","orcid":"https://orcid.org/0000-0001-8166-2441"},"institutions":[{"id":"https://openalex.org/I2801628138","display_name":"Frankfurt Institute for Advanced Studies","ror":"https://ror.org/05vmv8m79","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2801628138"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jochen Triesch","raw_affiliation_strings":["Frankfurt Institute for Advanced Studies, Germany","Frankfurt Institute for Advanced Studies, Frankfurt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Frankfurt Institute for Advanced Studies, Germany","institution_ids":["https://openalex.org/I2801628138"]},{"raw_affiliation_string":"Frankfurt Institute for Advanced Studies, Frankfurt, Germany","institution_ids":["https://openalex.org/I2801628138"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9921000003814697,"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/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8426409959793091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7489102482795715},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6878079771995544},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6826528906822205},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6101710796356201},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.5879511833190918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5310982465744019},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.495491623878479},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45571067929267883},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43605560064315796},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3663247227668762},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12139818072319031},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09129437804222107}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8426409959793091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7489102482795715},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6878079771995544},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6826528906822205},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6101710796356201},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.5879511833190918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310982465744019},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.495491623878479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45571067929267883},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43605560064315796},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3663247227668762},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12139818072319031},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09129437804222107},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/devlrn.2011.6037351","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2011.6037351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},{"id":"pmh:oai:nottingham-repository.worktribe.com:4754330","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/output/4754330","pdf_url":null,"source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"},{"id":"pmh:oai:zenodo.org:3430616","is_oa":true,"landing_page_url":"https://zenodo.org/record/3430616","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:nottingham-repository.worktribe.com:4754330","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/output/4754330","pdf_url":null,"source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W91815983","https://openalex.org/W1480676279","https://openalex.org/W1576452626","https://openalex.org/W1791871313","https://openalex.org/W1979215131","https://openalex.org/W1982912347","https://openalex.org/W2029232177","https://openalex.org/W2032230668","https://openalex.org/W2033580167","https://openalex.org/W2046713808","https://openalex.org/W2081672701","https://openalex.org/W2085170165","https://openalex.org/W2103006043","https://openalex.org/W2105549490","https://openalex.org/W2109910161","https://openalex.org/W2113122939","https://openalex.org/W2114958204","https://openalex.org/W2117726420","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2126449078","https://openalex.org/W2136202932","https://openalex.org/W2148819999","https://openalex.org/W2155390463","https://openalex.org/W2160371091","https://openalex.org/W2168342951","https://openalex.org/W2168358266","https://openalex.org/W2249258426","https://openalex.org/W2334782222","https://openalex.org/W2415632315","https://openalex.org/W2912185451","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W6603735088","https://openalex.org/W6628735244","https://openalex.org/W6634528131","https://openalex.org/W6638276159","https://openalex.org/W6677394234","https://openalex.org/W6680080562","https://openalex.org/W6683821272","https://openalex.org/W6715956157"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147"],"abstract_inverted_index":{"Reinforcement":[0],"Learning,":[1,4],"or":[2],"Reward-Dependent":[3],"has":[5],"been":[6],"very":[7],"successful":[8],"at":[9],"describing":[10,70],"how":[11,158],"animals":[12],"and":[13,24,61,96,106,122,156],"humans":[14],"adjust":[15],"their":[16,22,26,62],"actions":[17,60],"so":[18],"as":[19],"to":[20,58,66,112,159,162],"increase":[21],"gains":[23],"reduce":[25],"losses":[27],"in":[28,49,93,102,146],"a":[29,136],"wide":[30],"variety":[31],"of":[32,42,73,80,86,89,104,127],"tasks.":[33],"Empirical":[34],"studies":[35],"have":[36],"furthermore":[37],"identified":[38],"numerous":[39],"neuronal":[40],"correlates":[41],"quantities":[43],"necessary":[44],"for":[45,55,116,141],"such":[46],"computations.":[47],"But,":[48],"general":[50,144],"it":[51],"is":[52,111,129],"too":[53,131],"expensive":[54],"the":[56,71,74,78,90,94,99,125,142,148,163,168],"brain":[57],"encode":[59],"outcomes":[63],"with":[64,119],"respect":[65],"all":[67],"available":[68],"dimensions":[69,118],"state":[72],"world.":[75],"This":[76],"suggests":[77],"existence":[79],"learning":[81,139],"algorithms":[82],"that":[83],"are":[84,150],"capable":[85],"taking":[87],"advantage":[88],"independencies":[91],"present":[92],"world":[95],"hence":[97],"reducing":[98],"computational":[100],"costs":[101],"terms":[103],"representations":[105],"learning.":[107],"A":[108],"possible":[109],"solution":[110,140],"use":[113],"separate":[114],"learners":[115],"task":[117,169],"independent":[120,152],"dynamics":[121,149],"rewards.":[123],"But":[124],"condition":[126],"independence":[128],"usually":[130],"restrictive.":[132],"Here,":[133],"we":[134],"propose":[135],"hierarchical":[137],"reinforcement":[138],"more":[143],"case":[145],"which":[147,166],"not":[151],"but":[153],"weakly":[154],"coupled":[155],"show":[157],"assign":[160],"credit":[161],"different":[164],"modules,":[165],"solve":[167],"jointly.":[170]},"counts_by_year":[{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2016-06-24T00:00:00"}