{"id":"https://openalex.org/W2907251162","doi":"https://doi.org/10.1109/cec.2019.8790157","title":"Machine Teaching in Hierarchical Genetic Reinforcement Learning: Curriculum Design of Reward Functions for Swarm Shepherding","display_name":"Machine Teaching in Hierarchical Genetic Reinforcement Learning: Curriculum Design of Reward Functions for Swarm Shepherding","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2907251162","doi":"https://doi.org/10.1109/cec.2019.8790157","mag":"2907251162"},"language":"en","primary_location":{"id":"doi:10.1109/cec.2019.8790157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2019.8790157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1901.00949","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025807780","display_name":"Nicholas R. Clayton","orcid":null},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nicholas R. Clayton","raw_affiliation_strings":["School of Engineering & IT, University of New South Wales, Canberra, Australia","School of Engineering and IT, University of New South Wales, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering & IT, University of New South Wales, Canberra, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Engineering and IT, University of New South Wales, Canberra, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022974795","display_name":"Hussein A. Abbass","orcid":"https://orcid.org/0000-0002-8837-0748"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I40053085","display_name":"Australian Defence Force Academy","ror":"https://ror.org/02j5s7g39","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571","https://openalex.org/I40053085","https://openalex.org/I4394709116"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hussein Abbass","raw_affiliation_strings":["School of Engineering & IT, University of New South Wales, Canberra, Australia","AUSTRALIAN DEFENCE FORCE ACADEMY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering & IT, University of New South Wales, Canberra, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]},{"raw_affiliation_string":"AUSTRALIAN DEFENCE FORCE ACADEMY","institution_ids":["https://openalex.org/I40053085"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5487,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69838576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1259","last_page":"1266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9743000268936157,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7664133310317993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.691226065158844},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6264214515686035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5491575598716736},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5230006575584412},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.4473332166671753},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3818260431289673},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3344849944114685}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7664133310317993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.691226065158844},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6264214515686035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5491575598716736},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5230006575584412},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.4473332166671753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3818260431289673},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3344849944114685},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cec.2019.8790157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2019.8790157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1901.00949","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.00949","pdf_url":"https://arxiv.org/pdf/1901.00949","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1901.00949","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1901.00949","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2907251162","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1901.00949","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.00949","pdf_url":"https://arxiv.org/pdf/1901.00949","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2907251162.pdf","grobid_xml":"https://content.openalex.org/works/W2907251162.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1974014372","https://openalex.org/W2001773175","https://openalex.org/W2049287437","https://openalex.org/W2119120935","https://openalex.org/W2134493171","https://openalex.org/W2150312211","https://openalex.org/W2152033532","https://openalex.org/W2158548602","https://openalex.org/W2161205534","https://openalex.org/W2170591991","https://openalex.org/W2294637789","https://openalex.org/W2295904058","https://openalex.org/W2311971587","https://openalex.org/W2400329691","https://openalex.org/W2406612398","https://openalex.org/W2473394283","https://openalex.org/W2491785880","https://openalex.org/W2499574314","https://openalex.org/W2587233709","https://openalex.org/W2769558701","https://openalex.org/W2782946658","https://openalex.org/W2900835512","https://openalex.org/W4213113494","https://openalex.org/W4249373955","https://openalex.org/W6683443546","https://openalex.org/W6697152052","https://openalex.org/W6713821780","https://openalex.org/W6723874547","https://openalex.org/W6992654895"],"related_works":["https://openalex.org/W2968805005","https://openalex.org/W1996272383","https://openalex.org/W2801182767","https://openalex.org/W3040408533","https://openalex.org/W1994480928","https://openalex.org/W2581945288","https://openalex.org/W2070627246","https://openalex.org/W158722652","https://openalex.org/W2963905903","https://openalex.org/W47703557","https://openalex.org/W2129427976","https://openalex.org/W3111828986","https://openalex.org/W2355006797","https://openalex.org/W2967387967","https://openalex.org/W2320047991","https://openalex.org/W3111442723","https://openalex.org/W2418726961","https://openalex.org/W2990118443","https://openalex.org/W2963761387","https://openalex.org/W2979880457"],"abstract_inverted_index":{"The":[0,112,141],"design":[1,31,77,123],"of":[2,124],"reward":[3,33,47,78,139],"functions":[4,48,79],"in":[5,22,45,53,67,87,131],"reinforcement":[6,81,92,126],"learning":[7,134],"is":[8,18,118],"a":[9,28,38,54,72,89,96,102,109,137,145,162],"human":[10,29,39,51,68],"skill":[11],"that":[12,25,94,115,149],"comes":[13],"with":[14,128],"experience.":[15],"Unfortunately,":[16],"there":[17],"not":[19],"any":[20],"methodology":[21,75,86,117],"the":[23,32,42,85,116,122,132,151,167],"literature":[24],"could":[26],"guide":[27,121],"to":[30,36,40,49,70,76,100,120,160,165],"function":[34,148],"or":[35],"allow":[37],"transfer":[41],"skills":[43,155],"developed":[44],"designing":[46,88],"another":[50],"and":[52,154],"systematic":[55],"manner.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"use":[61],"Systematic":[62],"Instructional":[63],"Design,":[64],"an":[65,106],"approach":[66],"education,":[69],"engineer":[71],"machine":[73],"education":[74],"for":[80,105],"learning.":[82],"We":[83],"demonstrate":[84],"hierarchical":[90,125],"genetic":[91],"learner":[93],"adopts":[95],"neural":[97],"network":[98],"representation":[99],"evolve":[101],"swarm":[103],"controller":[104],"agent":[107],"shepherding":[108],"boids-based":[110],"swarm.":[111,168],"results":[113],"reveal":[114],"able":[119],"learners,":[127],"each":[129,158],"model":[130],"hierarchy":[133,142],"incrementally":[135],"through":[136],"multi-part":[138],"function.":[140],"acts":[143],"as":[144],"decision":[146],"fusion":[147],"combines":[150],"individual":[152],"behaviours":[153],"learnt":[156],"by":[157],"instruction":[159],"create":[161],"smart":[163],"shepherd":[164],"control":[166]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}