{"id":"https://openalex.org/W1994301837","doi":"https://doi.org/10.7148/2009-0180-0186","title":"Ethological Concepts In Hierarchical Reinforcement Learning And Control Of Intelligent Agents","display_name":"Ethological Concepts In Hierarchical Reinforcement Learning And Control Of Intelligent Agents","publication_year":2009,"publication_date":"2009-06-09","ids":{"openalex":"https://openalex.org/W1994301837","doi":"https://doi.org/10.7148/2009-0180-0186","mag":"1994301837"},"language":"en","primary_location":{"id":"doi:10.7148/2009-0180-0186","is_oa":false,"landing_page_url":"https://doi.org/10.7148/2009-0180-0186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2009 Proceedings edited by J. Otamendi, A. Bargiela, J. L. Montes, L. M. Doncel Pedrera","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/A5058831673","display_name":"Pavel Nahodil","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Pavel Nahodil","raw_affiliation_strings":["Czech Technical Univ. in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Technical Univ. in Prague","institution_ids":["https://openalex.org/I44504214"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5058831673"],"corresponding_institution_ids":["https://openalex.org/I44504214"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0901183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"180","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14082","display_name":"Modeling, Simulation, and Optimization","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2607","display_name":"Discrete Mathematics and Combinatorics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14082","display_name":"Modeling, Simulation, and Optimization","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2607","display_name":"Discrete Mathematics and Combinatorics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11810","display_name":"Complex Systems and Decision Making","score":0.9253000020980835,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8270092010498047},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7077779769897461},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5516124367713928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5261515974998474},{"id":"https://openalex.org/keywords/intelligent-control","display_name":"Intelligent control","score":0.4486921429634094},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3569718599319458},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35157930850982666}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8270092010498047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077779769897461},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5516124367713928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5261515974998474},{"id":"https://openalex.org/C82327864","wikidata":"https://www.wikidata.org/wiki/Q835100","display_name":"Intelligent control","level":2,"score":0.4486921429634094},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3569718599319458},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35157930850982666}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7148/2009-0180-0186","is_oa":false,"landing_page_url":"https://doi.org/10.7148/2009-0180-0186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2009 Proceedings edited by J. Otamendi, A. Bargiela, J. L. Montes, L. M. Doncel Pedrera","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W24275207","https://openalex.org/W1502872058","https://openalex.org/W1518224635","https://openalex.org/W1524563972","https://openalex.org/W1544974905","https://openalex.org/W1968375151","https://openalex.org/W2027045220","https://openalex.org/W2037433905","https://openalex.org/W2085756750","https://openalex.org/W2123826923","https://openalex.org/W2134437265","https://openalex.org/W2150339816","https://openalex.org/W4285719527"],"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":{"This":[0,96],"paper":[1],"integrates":[2],"rigorous":[3],"methods":[4,153,176],"of":[5,115,140,161],"reinforcement":[6],"learning":[7,126],"(RL)":[8],"and":[9,45,82,103,164],"control":[10,104],"engineering":[11],"with":[12,135],"a":[13,25,113],"behavioral":[14],"(ethology)":[15],"approach":[16],"to":[17,33,53,67,86,100,150,167,172,194],"the":[18,34,84,91,129,136,141,151,162,173,178,185,195,198],"agent":[19,80,85,92],"technology.":[20],"The":[21,39,56,70,138,157],"main":[22],"outcome":[23],"is":[24,98,105,146,182,190],"hybrid":[26],"architecture":[27,40],"for":[28],"intelligent":[29],"autonomous":[30,74],"agents":[31,58,71,130,158],"targeted":[32],"Artificial":[35],"Life":[36],"like":[37],"environments.":[38],"adopts":[41],"several":[42],"biology":[43],"concepts":[44],"shows":[46],"that":[47,89,154],"they":[48],"can":[49],"provide":[50,165],"robust":[51],"solutions":[52],"some":[54],"areas.":[55],"resulting":[57],"perform":[59,87],"from":[60,197],"primitive":[61],"behaviors,":[62,66],"simple":[63],"goal":[64],"directed":[65],"complex":[68],"planning.":[69],"are":[72,155],"fully":[73],"through":[75],"environment":[76],"feedback":[77],"evaluating":[78],"internal":[79],"state":[81],"motivate":[83],"behaviors":[88],"return":[90],"towards":[93],"optimal":[94,200],"conditions.":[95,201],"principle":[97],"typical":[99],"animals.":[101],"Learning":[102],"realized":[106],"by":[107,184],"multiple":[108],"RL":[109,168,175],"controllers":[110],"working":[111],"in":[112],"hierarchy":[114,145],"Semi":[116],"Markov":[117],"Decision":[118],"Processes":[119],"(SMDP).":[120],"Used":[121],"model":[122],"free":[123],"Q(\u03bb":[124],")":[125],"works":[127],"online,":[128],"gain":[131],"experiences":[132],"during":[133],"interaction":[134],"environment.":[137],"decomposition":[139],"root":[142],"SMDP":[143],"into":[144],"automated":[147],"as":[148,170],"opposed":[149,171],"conventional":[152,174],"manual.":[156],"assess":[159],"utility":[160],"behavior":[163,189],"rewards":[166,179],"controller":[169],"where":[177],"situations":[180],"map":[181],"defined":[183],"designer":[186],"upfront.":[187],"Agent":[188],"continuously":[191],"optimized":[192],"according":[193],"distance":[196],"agent\u2019s":[199]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}