{"id":"https://openalex.org/W4383220085","doi":"https://doi.org/10.1109/tie.2023.3290244","title":"Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping","display_name":"Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping","publication_year":2023,"publication_date":"2023-07-05","ids":{"openalex":"https://openalex.org/W4383220085","doi":"https://doi.org/10.1109/tie.2023.3290244"},"language":"en","primary_location":{"id":"doi:10.1109/tie.2023.3290244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tie.2023.3290244","pdf_url":null,"source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Electronics","raw_type":"journal-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/A5050486697","display_name":"Victor R. F. Miranda","orcid":"https://orcid.org/0000-0001-9653-6050"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Victor R. F. Miranda","raw_affiliation_strings":["Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-9653-6050","affiliations":[{"raw_affiliation_string":"Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083656237","display_name":"Armando Alves Neto","orcid":"https://orcid.org/0000-0002-4940-0377"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Armando A. Neto","raw_affiliation_strings":["Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-4940-0377","affiliations":[{"raw_affiliation_string":"Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034989154","display_name":"Gustavo Freitas","orcid":"https://orcid.org/0000-0001-5343-7028"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gustavo M. Freitas","raw_affiliation_strings":["Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-5343-7028","affiliations":[{"raw_affiliation_string":"Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090973041","display_name":"Leonardo Amaral Mozelli","orcid":"https://orcid.org/0000-0001-9986-3700"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leonardo A. Mozelli","raw_affiliation_strings":["Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-9986-3700","affiliations":[{"raw_affiliation_string":"Graduate Program in Electrical Engineering (PPGEE), Department of Electronics Engineering (DELT), Department of Electrical Engineering (DEE), Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.5122,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97406626,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"71","issue":"6","first_page":"6013","last_page":"6020"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.7466744184494019},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6973477005958557},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.6234433650970459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5978676676750183},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5937511920928955},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5752084255218506},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5743430256843567},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5296506881713867},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4490143954753876},{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.4353622496128082},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3677378296852112},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32201439142227173},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18539810180664062},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14633721113204956},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07597863674163818}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7466744184494019},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6973477005958557},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.6234433650970459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5978676676750183},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5937511920928955},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5752084255218506},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5743430256843567},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5296506881713867},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4490143954753876},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.4353622496128082},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3677378296852112},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32201439142227173},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18539810180664062},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14633721113204956},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07597863674163818},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tie.2023.3290244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tie.2023.3290244","pdf_url":null,"source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2088930693","display_name":null,"funder_award_id":"310446/2021-0","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G2556352422","display_name":null,"funder_award_id":"407063/2021-8","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G372683529","display_name":null,"funder_award_id":"3APQ-02228-22","funder_id":"https://openalex.org/F4320322980","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais"},{"id":"https://openalex.org/G8347442190","display_name":null,"funder_award_id":"306286/2020-3","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322980","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais","ror":"https://ror.org/00nc55f03"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2153340051","https://openalex.org/W2605102758","https://openalex.org/W2767050701","https://openalex.org/W2808470116","https://openalex.org/W2906415336","https://openalex.org/W2909906617","https://openalex.org/W2954996726","https://openalex.org/W2963390419","https://openalex.org/W2963428623","https://openalex.org/W2972350003","https://openalex.org/W3028077456","https://openalex.org/W3028803129","https://openalex.org/W3031447301","https://openalex.org/W3090307871","https://openalex.org/W3092166936","https://openalex.org/W3095315965","https://openalex.org/W3100153298","https://openalex.org/W3101442004","https://openalex.org/W3131482536","https://openalex.org/W3158253560","https://openalex.org/W3161551690","https://openalex.org/W3162002595","https://openalex.org/W3186502870","https://openalex.org/W3194634940","https://openalex.org/W3194805530","https://openalex.org/W3196603038","https://openalex.org/W3207080284","https://openalex.org/W3213746858","https://openalex.org/W4210939259","https://openalex.org/W4214717370","https://openalex.org/W4286375451","https://openalex.org/W4315487473","https://openalex.org/W6684921986","https://openalex.org/W6748839928","https://openalex.org/W6756840741","https://openalex.org/W6777834836","https://openalex.org/W6784098896","https://openalex.org/W6785204124"],"related_works":["https://openalex.org/W1992503747","https://openalex.org/W2371519816","https://openalex.org/W2043154226","https://openalex.org/W2369529107","https://openalex.org/W2329043542","https://openalex.org/W2109948066","https://openalex.org/W1678858522","https://openalex.org/W3195090107","https://openalex.org/W2375684291","https://openalex.org/W38056103"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,12,62,89,96,102,111,144,154],"application":[4],"of":[5,14,71,128,149],"Deep":[6],"Reinforcement":[7],"Learning":[8],"(DRL)":[9],"methods":[10,146],"in":[11,25,74,88,147,159],"context":[13],"local":[15,50,165],"navigation,":[16],"i.e.,":[17],"a":[18,22,108],"robot":[19],"moves":[20],"towards":[21],"goal":[23],"location":[24],"unknown":[26],"and":[27,132,167],"cluttered":[28],"workspaces":[29],"equipped":[30],"only":[31],"with":[32],"limited-range":[33],"exteroceptive":[34],"sensors.":[35],"Collision":[36],"avoidance":[37],"policies":[38],"based":[39],"on":[40],"DRL":[41],"present":[42],"advantages,":[43],"but":[44],"they":[45],"are":[46,162],"quite":[47],"susceptible":[48],"to":[49,55,61,94,99,164],"minima,":[51],"once":[52],"their":[53],"capacity":[54,98],"learn":[56],"suitable":[57],"actions":[58],"is":[59,92],"limited":[60],"sensor":[63],"range.":[64],"We":[65],"address":[66],"this":[67],"issue":[68],"by":[69,151],"means":[70],"reward":[72,79,141],"shaping":[73,142],"actorcritic":[75],"networks.":[76],"A":[77,126],"dense":[78],"function,":[80],"that":[81,138,161],"incorporates":[82],"<italic":[83,129,133],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[84,130,134],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">map":[85],"information</i>":[86],"gained":[87],"training":[90,123],"stage,":[91],"proposed":[93,140],"increase":[95],"agent's":[97],"decide":[100],"about":[101],"best":[103],"action.":[104],"Also,":[105],"we":[106],"offer":[107],"comparison":[109],"between":[110],"Twin":[112],"Delayed":[113],"Deep-Deterministic":[114],"Policy":[115],"Gradient":[116],"(TD3)":[117],"andSoft":[118],"Actor-Critic":[119],"(SAC)":[120],"algorithms":[121],"for":[122],"our":[124,139],"policy.":[125],"set":[127],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">sim-to-sim</i>":[131],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">sim-to-real</i>":[135],"trials":[136],"illustrate":[137],"outperforms":[143],"compared":[145],"terms":[148],"generalization,":[150],"arriving":[152],"at":[153,156],"target":[155],"higher":[157],"rates":[158],"maps":[160],"prone":[163],"minima":[166],"collisions.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}