{"id":"https://openalex.org/W2494907211","doi":"https://doi.org/10.1109/cec.2017.7969297","title":"Neuroevolution-based Inverse Reinforcement Learning","display_name":"Neuroevolution-based Inverse Reinforcement Learning","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W2494907211","doi":"https://doi.org/10.1109/cec.2017.7969297","mag":"2494907211"},"language":"en","primary_location":{"id":"doi:10.1109/cec.2017.7969297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2017.7969297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1608.02971","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022988118","display_name":"Karan K. Budhraja","orcid":"https://orcid.org/0000-0002-3683-2234"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karan K. Budhraja","raw_affiliation_strings":["Computer Science and Electrical Engineering, University of Maryland, Baltimore, Baltimore County, USA","University of Maryland,Baltimore County"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Electrical Engineering, University of Maryland, Baltimore, Baltimore County, USA","institution_ids":["https://openalex.org/I79272384"]},{"raw_affiliation_string":"University of Maryland,Baltimore County","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114778025","display_name":"Tim Oates","orcid":"https://orcid.org/0000-0002-8655-747X"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Oates","raw_affiliation_strings":["Computer Science and Electrical Engineering, University of Maryland, Baltimore, Baltimore County, USA","University of Maryland,Baltimore County"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Electrical Engineering, University of Maryland, Baltimore, Baltimore County, USA","institution_ids":["https://openalex.org/I79272384"]},{"raw_affiliation_string":"University of Maryland,Baltimore County","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79272384"],"apc_list":null,"apc_paid":null,"fwci":0.1993,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59753351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"67","last_page":"76"},"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9969000220298767,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9966999888420105,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.858202338218689},{"id":"https://openalex.org/keywords/neuroevolution","display_name":"Neuroevolution","score":0.7892961502075195},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7033216953277588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6762332916259766},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5776819586753845},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5566102266311646},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5548902153968811},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5450504422187805},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5310314893722534},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4727398157119751},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.22421333193778992},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14702445268630981}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.858202338218689},{"id":"https://openalex.org/C118070581","wikidata":"https://www.wikidata.org/wiki/Q2060528","display_name":"Neuroevolution","level":3,"score":0.7892961502075195},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7033216953277588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6762332916259766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5776819586753845},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5566102266311646},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5548902153968811},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5450504422187805},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5310314893722534},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4727398157119751},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.22421333193778992},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14702445268630981},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/cec.2017.7969297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2017.7969297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1608.02971","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.02971","pdf_url":"https://arxiv.org/pdf/1608.02971","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"pmh:oai:mdsoar.org:11603/15472","is_oa":true,"landing_page_url":"http://hdl.handle.net/11603/15472","pdf_url":"http://hdl.handle.net/11603/15472","source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","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":"Original File Name: Budhraja_umbc_0434M_11424.pdf","raw_type":"Text"},{"id":"mag:2494907211","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1608.02971v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:pqdtoai.proquest.com:10140581","is_oa":false,"landing_page_url":"http://pqdtopen.proquest.com/#viewpdf?dispub=10140581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"thesis"},{"id":"doi:10.48550/arxiv.1608.02971","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1608.02971","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"doi:10.13016/m2je0c-m0d3","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2je0c-m0d3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"Collection"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1608.02971","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.02971","pdf_url":"https://arxiv.org/pdf/1608.02971","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W52153049","https://openalex.org/W52822972","https://openalex.org/W64088143","https://openalex.org/W157687528","https://openalex.org/W648129165","https://openalex.org/W757745030","https://openalex.org/W1494902192","https://openalex.org/W1544131626","https://openalex.org/W1564754565","https://openalex.org/W1567512734","https://openalex.org/W1569757501","https://openalex.org/W1574859627","https://openalex.org/W1576818901","https://openalex.org/W1591675293","https://openalex.org/W1600941617","https://openalex.org/W1746819321","https://openalex.org/W1965555277","https://openalex.org/W2043962331","https://openalex.org/W2061562262","https://openalex.org/W2072128103","https://openalex.org/W2093335754","https://openalex.org/W2093524643","https://openalex.org/W2096232175","https://openalex.org/W2096645045","https://openalex.org/W2099620844","https://openalex.org/W2105156548","https://openalex.org/W2111935653","https://openalex.org/W2117675763","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2128002512","https://openalex.org/W2128241916","https://openalex.org/W2129018774","https://openalex.org/W2134514463","https://openalex.org/W2138784882","https://openalex.org/W2140685838","https://openalex.org/W2145060720","https://openalex.org/W2147596804","https://openalex.org/W2150341604","https://openalex.org/W2162009473","https://openalex.org/W2163037893","https://openalex.org/W2168909409","https://openalex.org/W2177382477","https://openalex.org/W2229542245","https://openalex.org/W2267646830","https://openalex.org/W4205947740","https://openalex.org/W4238753141","https://openalex.org/W6605534957","https://openalex.org/W6674884181","https://openalex.org/W6677555207","https://openalex.org/W6679244825","https://openalex.org/W6681439324","https://openalex.org/W6683921772","https://openalex.org/W6684097133","https://openalex.org/W6685026872","https://openalex.org/W6685353786"],"related_works":["https://openalex.org/W2117675763","https://openalex.org/W2491675558","https://openalex.org/W69730760","https://openalex.org/W2156163138","https://openalex.org/W2984409990","https://openalex.org/W2765297602","https://openalex.org/W2899685447","https://openalex.org/W2888519432","https://openalex.org/W3130800560","https://openalex.org/W1971913572","https://openalex.org/W2947612938","https://openalex.org/W2024191559","https://openalex.org/W1552148478","https://openalex.org/W1600824415","https://openalex.org/W2949846483","https://openalex.org/W1640646391","https://openalex.org/W3106008061","https://openalex.org/W2080759927","https://openalex.org/W2166265228","https://openalex.org/W2967645217"],"abstract_inverted_index":{"The":[0,85,154],"problem":[1,198],"of":[2,101,110,148],"Learning":[3,20,46,96,143],"from":[4,21,69],"Demonstration":[5,22],"is":[6,23,87,156,219],"targeted":[7],"at":[8],"learning":[9],"to":[10,19,32,43,67,77,82,120,125,151,158,182],"perform":[11],"tasks":[12],"based":[13,55],"on":[14,56,59,135],"observed":[15,31,121,157],"examples.":[16],"One":[17],"approach":[18,42],"Inverse":[24,44,94,141],"Reinforcement":[25,45,95,142],"Learning,":[26],"in":[27,112,117,170,177,189],"which":[28,171],"actions":[29],"are":[30,65,75,174],"infer":[33],"rewards.":[34],"This":[35,115,129,180],"work":[36,130,134],"combines":[37],"a":[38,49,60,70,79,163],"feature-based":[39,93],"state":[40,113,178],"evaluation":[41],"with":[47],"neuroevolution,":[48],"paradigm":[50],"for":[51,107,140,162],"modifying":[52],"neural":[53,104],"networks":[54,64,105],"their":[57],"performance":[58,214],"given":[61],"task.":[62],"Neural":[63],"used":[66],"learn":[68],"demonstrated":[71],"expert":[72],"policy":[73,80],"and":[74,89,191],"evolved":[76],"generate":[78],"similar":[81],"the":[83,99,194,205],"demonstration.":[84],"algorithm":[86,155],"discussed":[88],"evaluated":[90,217],"against":[91],"competitive":[92],"approaches.":[97],"At":[98],"cost":[100],"execution":[102],"time,":[103],"allow":[106],"non-linear":[108,146],"combinations":[109,147],"features":[111],"evaluations.":[114],"results":[116],"better":[118],"correspondence":[119],"examples":[122],"as":[123,187],"opposed":[124],"using":[126,145],"linear":[127],"combinations.":[128],"also":[131],"extends":[132],"existing":[133],"Bayesian":[136],"Non-Parametric":[137],"Feature":[138],"construction":[139],"by":[144],"intermediate":[149],"data":[150],"improve":[152],"performance.":[153],"be":[159,209],"specifically":[160],"suitable":[161],"linearly":[164],"solvable":[165],"non-deterministic":[166],"Markov":[167],"Decision":[168],"Processes":[169],"multiple":[172],"rewards":[173],"sparsely":[175],"scattered":[176],"space.":[179],"translates":[181],"real-world":[183],"control":[184],"problems":[185],"such":[186],"those":[188],"robotics":[190],"automation":[192],"(e.g.":[193],"robust":[195],"output":[196],"tracking":[197],"or":[199],"controlling":[200],"an":[201],"n-joint":[202],"arm),":[203],"where":[204],"underlying":[206],"equations":[207],"can":[208],"made":[210],"linear.":[211],"A":[212],"conclusive":[213],"hierarchy":[215],"between":[216],"algorithms":[218],"presented.":[220]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}