{"id":"https://openalex.org/W3111962634","doi":"https://doi.org/10.1109/icdl-epirob48136.2020.9278049","title":"From Reward to Histone: Combining Temporal-Difference Learning and Epigenetic Inheritance for Swarm's Coevolving Decision Making","display_name":"From Reward to Histone: Combining Temporal-Difference Learning and Epigenetic Inheritance for Swarm's Coevolving Decision Making","publication_year":2020,"publication_date":"2020-10-26","ids":{"openalex":"https://openalex.org/W3111962634","doi":"https://doi.org/10.1109/icdl-epirob48136.2020.9278049","mag":"3111962634"},"language":"en","primary_location":{"id":"doi:10.1109/icdl-epirob48136.2020.9278049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl-epirob48136.2020.9278049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://unsworks.unsw.edu.au/bitstreams/1aaabb86-2d84-4fba-9e72-334fdb549b60/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011421800","display_name":"Faqihza Mukhlish","orcid":"https://orcid.org/0000-0002-7639-0119"},"institutions":[{"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":"Faqihza Mukhlish","raw_affiliation_strings":["School of Mechanical and Manufacturing Engineering, University of New South Wales, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Manufacturing Engineering, University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101884354","display_name":"John Page","orcid":"https://orcid.org/0000-0002-6083-255X"},"institutions":[{"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":"John Page","raw_affiliation_strings":["School of Mechanical and Manufacturing Engineering, University of New South Wales, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Manufacturing Engineering, University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058225317","display_name":"Michael Bain","orcid":"https://orcid.org/0000-0002-4309-6511"},"institutions":[{"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":"Michael Bain","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9954000115394592,"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":0.9954000115394592,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9815000295639038,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/epigenetics","display_name":"Epigenetics","score":0.73599773645401},{"id":"https://openalex.org/keywords/inheritance","display_name":"Inheritance (genetic algorithm)","score":0.593087375164032},{"id":"https://openalex.org/keywords/epigenome","display_name":"Epigenome","score":0.587871253490448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5858931541442871},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5800407528877258},{"id":"https://openalex.org/keywords/evolutionary-robotics","display_name":"Evolutionary robotics","score":0.5632773041725159},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.5408042669296265},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.5204318165779114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47590383887290955},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45513594150543213},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.4314798414707184},{"id":"https://openalex.org/keywords/swarm-intelligence","display_name":"Swarm intelligence","score":0.41360852122306824},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3623524308204651},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29539939761161804},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.21655645966529846},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.21144640445709229},{"id":"https://openalex.org/keywords/dna-methylation","display_name":"DNA methylation","score":0.21129602193832397},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13642331957817078}],"concepts":[{"id":"https://openalex.org/C41091548","wikidata":"https://www.wikidata.org/wiki/Q26939","display_name":"Epigenetics","level":3,"score":0.73599773645401},{"id":"https://openalex.org/C2780902518","wikidata":"https://www.wikidata.org/wiki/Q6033780","display_name":"Inheritance (genetic algorithm)","level":3,"score":0.593087375164032},{"id":"https://openalex.org/C117717151","wikidata":"https://www.wikidata.org/wiki/Q3589155","display_name":"Epigenome","level":5,"score":0.587871253490448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5858931541442871},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5800407528877258},{"id":"https://openalex.org/C199505168","wikidata":"https://www.wikidata.org/wiki/Q3267529","display_name":"Evolutionary robotics","level":3,"score":0.5632773041725159},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.5408042669296265},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.5204318165779114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47590383887290955},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45513594150543213},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.4314798414707184},{"id":"https://openalex.org/C119487961","wikidata":"https://www.wikidata.org/wiki/Q863960","display_name":"Swarm intelligence","level":3,"score":0.41360852122306824},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3623524308204651},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29539939761161804},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.21655645966529846},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.21144640445709229},{"id":"https://openalex.org/C190727270","wikidata":"https://www.wikidata.org/wiki/Q874745","display_name":"DNA methylation","level":4,"score":0.21129602193832397},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13642331957817078},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icdl-epirob48136.2020.9278049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl-epirob48136.2020.9278049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"},{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/unsworks_73336","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/unsworks_73336","pdf_url":"https://unsworks.unsw.edu.au/bitstreams/1aaabb86-2d84-4fba-9e72-334fdb549b60/download","source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), Valpara\u00edso, Chile, 2020-10-26 - 2020-10-30","raw_type":"http://purl.org/coar/resource_type/c_5794"},{"id":"pmh:doi:10.26190/unsworks/27910","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"conference paper"},{"id":"doi:10.26190/unsworks/27910","is_oa":true,"landing_page_url":"https://doi.org/10.26190/unsworks/27910","pdf_url":null,"source":{"id":"https://openalex.org/S7407053176","display_name":"University of New South Wales","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/unsworks_73336","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/unsworks_73336","pdf_url":"https://unsworks.unsw.edu.au/bitstreams/1aaabb86-2d84-4fba-9e72-334fdb549b60/download","source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), Valpara\u00edso, Chile, 2020-10-26 - 2020-10-30","raw_type":"http://purl.org/coar/resource_type/c_5794"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3111962634.pdf","grobid_xml":"https://content.openalex.org/works/W3111962634.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1151620346","https://openalex.org/W1479809530","https://openalex.org/W1518858799","https://openalex.org/W1567760409","https://openalex.org/W1651256951","https://openalex.org/W1659842140","https://openalex.org/W1968074400","https://openalex.org/W2006290617","https://openalex.org/W2015472341","https://openalex.org/W2052255197","https://openalex.org/W2052821420","https://openalex.org/W2069713835","https://openalex.org/W2099511120","https://openalex.org/W2113485341","https://openalex.org/W2118331730","https://openalex.org/W2121863487","https://openalex.org/W2124188359","https://openalex.org/W2149469814","https://openalex.org/W2151083897","https://openalex.org/W2174841307","https://openalex.org/W2228404248","https://openalex.org/W2280718773","https://openalex.org/W2331714173","https://openalex.org/W2591309159","https://openalex.org/W2761382041","https://openalex.org/W2869799801","https://openalex.org/W3019123247","https://openalex.org/W3023540311","https://openalex.org/W3111962634","https://openalex.org/W3156330606","https://openalex.org/W4214717370","https://openalex.org/W6636907291","https://openalex.org/W6776471057"],"related_works":["https://openalex.org/W4308079021","https://openalex.org/W1527337688","https://openalex.org/W2399799070","https://openalex.org/W2048054807","https://openalex.org/W2746377055","https://openalex.org/W4386001959","https://openalex.org/W2594296178","https://openalex.org/W3089846858","https://openalex.org/W3012322385","https://openalex.org/W4304182880"],"abstract_inverted_index":{"Applying":[0],"intelligence":[1],"to":[2,22,36,73,124,136,178,189],"a":[3,31,34,39,56,71,78,95,144],"group":[4],"of":[5,45,88,159,175,181],"simple":[6],"robots":[7,11],"known":[8],"as":[9,143],"swarm":[10,35,96],"has":[12],"become":[13],"an":[14],"exciting":[15],"technology":[16],"in":[17,38,55,62,77,100,112],"assisting":[18],"or":[19],"replacing":[20],"humans":[21],"fulfil":[23],"complex,":[24],"dangerous":[25],"and":[26,48,121,128,140,161],"harsh":[27],"missions.":[28],"However,":[29],"building":[30],"strategy":[32,72],"for":[33,94],"thrive":[37],"dynamic":[40],"environment":[41,80],"is":[42,110,150],"challenging":[43],"because":[44],"control":[46],"decentralisation":[47],"interactions":[49],"between":[50],"agents.":[51],"The":[52,131,156,169],"decision-making":[53],"process":[54,146,171],"robotic":[57],"task":[58],"commonly":[59],"takes":[60],"place":[61],"sequential":[63],"stages.":[64],"By":[65],"understanding":[66],"the":[67,86,166,173,176,182,187],"subsequent":[68],"action-reaction":[69],"process,":[70],"make":[74],"optimal":[75,126],"decisions":[76],"respective":[79],"can":[81],"be":[82,98],"learnt.":[83],"Hence,":[84],"using":[85,106],"concept":[87],"epigenetic":[89,107,122,162],"inheritance,":[90],"novel":[91],"evolutionary-learning":[92],"mechanisms":[93,185],"will":[97],"discussed":[99],"this":[101,113],"paper.":[102],"Reinforcement":[103],"evolutionary":[104,141],"learning":[105,139],"inheritance":[108,123],"(RELEpi)":[109],"proposed":[111,132],"article.":[114],"This":[115],"method":[116,133],"utilizes":[117],"reward,":[118],"temporal":[119],"difference":[120],"approximate":[125],"action":[127],"behaviour":[129],"policies.":[130],"opens":[134],"possibilities":[135],"combine":[137],"reward-based":[138],"methods":[142],"stacked":[145],"where":[147],"histone":[148,179,196],"value":[149,180],"used":[151],"rather":[152],"than":[153],"fitness":[154],"function.":[155],"formulation":[157],"consists":[158],"methylation":[160,170],"mechanisms,":[163],"inspired":[164],"by":[165],"epigenome":[167],"studies.":[168],"helps":[172],"accumulation":[174],"reward":[177],"gene.":[183],"Epigenetic":[184],"give":[186],"ability":[188],"mate":[190],"genetic":[191],"information":[192],"along":[193],"with":[194],"their":[195],"value.":[197]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}