{"id":"https://openalex.org/W2082953382","doi":"https://doi.org/10.1145/2330163.2330178","title":"Hierarchical task decomposition through symbiosis in reinforcement learning","display_name":"Hierarchical task decomposition through symbiosis in reinforcement learning","publication_year":2012,"publication_date":"2012-07-07","ids":{"openalex":"https://openalex.org/W2082953382","doi":"https://doi.org/10.1145/2330163.2330178","mag":"2082953382"},"language":"en","primary_location":{"id":"doi:10.1145/2330163.2330178","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2330163.2330178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th annual conference on Genetic and evolutionary computation","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/A5015078188","display_name":"John A. Doucette","orcid":"https://orcid.org/0000-0003-4916-6258"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"John A. Doucette","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004241713","display_name":"Peter Lichodzijewski","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Peter Lichodzijewski","raw_affiliation_strings":["Dalhousie University, Halifax, NS, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003699164","display_name":"Malcolm I. Heywood","orcid":"https://orcid.org/0000-0002-1521-0671"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Malcolm I. Heywood","raw_affiliation_strings":["Dalhousie University, Halifax, NS, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3415,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.89653177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9958000183105469,"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9663000106811523,"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":0.8363434672355652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7147355675697327},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6463695168495178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6376882791519165},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6285467743873596},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6122512221336365},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5996135473251343},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5754792094230652},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5630443096160889},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5005908012390137},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4738914370536804},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.46484464406967163},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.43275225162506104},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12204161286354065},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11140593886375427}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8363434672355652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147355675697327},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6463695168495178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6376882791519165},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6285467743873596},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6122512221336365},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5996135473251343},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5754792094230652},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5630443096160889},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5005908012390137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4738914370536804},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.46484464406967163},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.43275225162506104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12204161286354065},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11140593886375427},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2330163.2330178","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2330163.2330178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th annual conference on Genetic and evolutionary computation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.6399999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322337","display_name":"Killam Trusts","ror":"https://ror.org/021cbtn85"},{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W30709480","https://openalex.org/W1482548745","https://openalex.org/W1515851193","https://openalex.org/W1588942736","https://openalex.org/W1850497332","https://openalex.org/W1914583973","https://openalex.org/W1981114175","https://openalex.org/W1985849007","https://openalex.org/W2013232999","https://openalex.org/W2067334388","https://openalex.org/W2096719600","https://openalex.org/W2101524054","https://openalex.org/W2101804758","https://openalex.org/W2104245950","https://openalex.org/W2106469529","https://openalex.org/W2107726111","https://openalex.org/W2107899042","https://openalex.org/W2111935653","https://openalex.org/W2113122939","https://openalex.org/W2121863487","https://openalex.org/W2128281152","https://openalex.org/W2163467402","https://openalex.org/W2169157770","https://openalex.org/W2263500441","https://openalex.org/W2285110183","https://openalex.org/W2744301119","https://openalex.org/W4246463991","https://openalex.org/W4256361765","https://openalex.org/W6635224564","https://openalex.org/W6646760115","https://openalex.org/W6653659043","https://openalex.org/W6676007687"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2912947802","https://openalex.org/W2037601570","https://openalex.org/W2123856982","https://openalex.org/W1530089576"],"abstract_inverted_index":{"Adopting":[0],"a":[1,17,20,71,119,151],"symbiotic":[2,129],"model":[3],"of":[4,58,74,108,154],"evolution":[5],"separates":[6],"context":[7],"for":[8,22,70,80,136],"deploying":[9],"an":[10,55,115],"action":[11,14],"from":[12,62,97],"the":[13,49,63,67,78,90,106,123,137],"itself.":[15],"Such":[16],"separation":[18],"provides":[19,77],"mechanism":[21],"task":[23,50],"decomposition":[24],"in":[25,54],"temporal":[26],"sequence":[27],"learning.":[28],"Moreover,":[29,143],"previously":[30],"learned":[31],"policies":[32],"are":[33,43,148],"taken":[34],"to":[35,48,95,104,133],"be":[36,52],"synonymous":[37],"with":[38,158],"meta":[39],"actions":[40,69],"(actions":[41],"that":[42],"themselves":[44],"policies).":[45],"Should":[46],"solutions":[47,61,147,160],"not":[51,101],"forthcoming":[53],"initial":[56,156],"round":[57,65,73],"evolution,":[59],"then":[60],"earlier":[64],"represent":[66],"'meta'":[68],"new":[72],"evolution.":[75],"This":[76],"basis":[79],"evolving":[81],"policy":[82],"trees.":[83],"A":[84],"benchmarking":[85],"study":[86],"is":[87,131],"performed":[88],"using":[89,114],"Acrobot":[91,124,155],"handstand":[92],"task.":[93],"Solutions":[94],"date":[96],"reinforcement":[98],"learning":[99],"have":[100],"been":[102],"able":[103,132],"approach":[105,130],"performance":[107],"those":[109],"established":[110],"14":[111],"years":[112],"ago":[113],"A*":[116],"search":[117],"and":[118],"priori":[120],"knowledge":[121],"regarding":[122],"energy":[125],"equations.":[126],"The":[127],"proposed":[128],"match":[134],"and,":[135],"first":[138],"time,":[139],"better":[140,163],"these":[141],"results.":[142],"unlike":[144],"previous":[145],"work,":[146],"tested":[149],"under":[150],"broad":[152],"range":[153],"conditions,":[157],"hierarchical":[159],"providing":[161],"significantly":[162],"generalization":[164],"performance.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}