{"id":"https://openalex.org/W4377966879","doi":"https://doi.org/10.1109/access.2023.3279729","title":"Decoding Reinforcement Learning for newcomers","display_name":"Decoding Reinforcement Learning for newcomers","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4377966879","doi":"https://doi.org/10.1109/access.2023.3279729"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3279729","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3279729","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10132462.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10132462.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071906297","display_name":"Francisco S. Neves","orcid":"https://orcid.org/0000-0003-4366-6227"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]},{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Francisco S. Neves","raw_affiliation_strings":["Centre for Robotics and Autonomous Systems, INESC TEC, Porto, Portugal","Department of Electrical and Computer Engineering, University of Porto, Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-4366-6227","affiliations":[{"raw_affiliation_string":"Centre for Robotics and Autonomous Systems, INESC TEC, Porto, Portugal","institution_ids":["https://openalex.org/I4210166615"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048254521","display_name":"Gustavo A. Andrade","orcid":"https://orcid.org/0000-0002-0298-220X"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Gustavo A. Andrade","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Universidade do Porto, Porto, Portugal","SYSTEC, ARISE, Faculty of Engineering, University of Porto, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Universidade do Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"SYSTEC, ARISE, Faculty of Engineering, University of Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064057300","display_name":"Matheus F. Reis","orcid":"https://orcid.org/0000-0001-9958-5958"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Matheus F. Reis","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Universidade do Porto, Porto, Portugal","SYSTEC, ARISE, Faculty of Engineering, University of Porto, Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-9958-5958","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Universidade do Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]},{"raw_affiliation_string":"SYSTEC, ARISE, Faculty of Engineering, University of Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069883451","display_name":"A. Pedro Aguiar","orcid":"https://orcid.org/0000-0001-7105-0505"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"A. Pedro Aguiar","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Universidade do Porto, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Universidade do Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004154927","display_name":"Andry Maykol Pinto","orcid":"https://orcid.org/0000-0003-2465-5813"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]},{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Andry M. Pinto","raw_affiliation_strings":["Centre for Robotics and Autonomous Systems, INESC TEC, Porto, Portugal","Department of Electrical and Computer Engineering, University of Porto, Porto, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-2465-5813","affiliations":[{"raw_affiliation_string":"Centre for Robotics and Autonomous Systems, INESC TEC, Porto, Portugal","institution_ids":["https://openalex.org/I4210166615"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071906297"],"corresponding_institution_ids":["https://openalex.org/I182534213","https://openalex.org/I4210166615"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.1657,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53117416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9905999898910522,"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/T12288","display_name":"Optimization and Search Problems","score":0.9681000113487244,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.7443325519561768},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.7289202213287354},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6517082452774048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6288025975227356},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5526564121246338},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5435500144958496},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5118857622146606},{"id":"https://openalex.org/keywords/educational-robotics","display_name":"Educational robotics","score":0.4303925931453705},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11084738373756409}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443325519561768},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.7289202213287354},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6517082452774048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6288025975227356},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5526564121246338},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5435500144958496},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5118857622146606},{"id":"https://openalex.org/C183889225","wikidata":"https://www.wikidata.org/wiki/Q5341299","display_name":"Educational robotics","level":4,"score":0.4303925931453705},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11084738373756409}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3279729","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3279729","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10132462.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:10017f2f6525414494de52f7a0d0a811","is_oa":true,"landing_page_url":"https://doaj.org/article/10017f2f6525414494de52f7a0d0a811","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 52778-52789 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3279729","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3279729","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10132462.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1412824535","display_name":null,"funder_award_id":"871571","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G4627546747","display_name":null,"funder_award_id":"P2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5281965400","display_name":null,"funder_award_id":"871571","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4377966879.pdf","grobid_xml":"https://content.openalex.org/works/W4377966879.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1771410628","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2765302304","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2789824229","https://openalex.org/W2803308811","https://openalex.org/W2892490014","https://openalex.org/W2907537824","https://openalex.org/W2907953482","https://openalex.org/W2938421504","https://openalex.org/W2959298928","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2973184394","https://openalex.org/W2981759303","https://openalex.org/W2991232381","https://openalex.org/W3126321819","https://openalex.org/W3155824738","https://openalex.org/W3156142002","https://openalex.org/W3165342365","https://openalex.org/W3189133245","https://openalex.org/W4213433215","https://openalex.org/W4214717370","https://openalex.org/W4251032819","https://openalex.org/W4293396018","https://openalex.org/W4294410918","https://openalex.org/W4297797010","https://openalex.org/W4298857966","https://openalex.org/W4298876402","https://openalex.org/W4321392130","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6683300800","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6739585900","https://openalex.org/W6741002519","https://openalex.org/W6741519989","https://openalex.org/W6744378193","https://openalex.org/W6744927671","https://openalex.org/W6747473740","https://openalex.org/W6748638692","https://openalex.org/W6748817170","https://openalex.org/W6748839928","https://openalex.org/W6751629939","https://openalex.org/W6754878628","https://openalex.org/W6757380569","https://openalex.org/W6758223966"],"related_works":["https://openalex.org/W3184683492","https://openalex.org/W4244213135","https://openalex.org/W2494230889","https://openalex.org/W2943610907","https://openalex.org/W2548796344","https://openalex.org/W2972718276","https://openalex.org/W4206307518","https://openalex.org/W2889355398","https://openalex.org/W2083091378","https://openalex.org/W4312927794"],"abstract_inverted_index":{"The":[0,22,81,182],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"paradigm":[4],"is":[5,27,102,130,140,145,192],"showing":[6],"promising":[7],"results":[8,183],"as":[9,43,194],"a":[10,106,124,149,156,188],"generic":[11],"purpose":[12],"framework":[13],"for":[14,68,104,134],"solving":[15,105],"decision-making":[16],"problems":[17],"(e.g.,":[18,73,142],"robotics,":[19],"games,":[20],"finance).":[21],"aim":[23],"of":[24,63,91,158,166],"this":[25,99,168],"work":[26],"to":[28,40,47,115,122,155,178,196],"reduce":[29,197],"the":[30,61,85,88,112,138,143,164,180,198],"learning":[31,199],"barriers":[32,200],"and":[33,38,60,79,96,132],"inspire":[34],"young":[35],"students,":[36],"researchers":[37,78],"educators":[39],"use":[41],"RL":[42,57,101],"an":[44,54,64,174],"obvious":[45],"tool":[46,83,177],"solve":[48],"robotics":[49,107],"problems.":[50],"This":[51],"paper":[52,169],"provides":[53],"intelligible":[55],"step-by-step":[56],"problem":[58,94,110,129],"formulation":[59,95],"availability":[62],"easy-to-use":[65],"interactive":[66,82,161],"simulator":[67],"students":[69],"at":[70],"various":[71],"levels":[72],"undergraduate,":[74],"bachelor,":[75],"master,":[76],"doctorate),":[77],"educators.":[80],"facilitates":[84],"familiarization":[86],"with":[87,118,173],"key":[89],"concepts":[90],"RL,":[92,167],"its":[93],"implementation.":[97],"In":[98],"work,":[100],"used":[103],"2D":[108],"navigational":[109,128],"where":[111],"robot":[113],"needs":[114],"avoid":[116],"collisions":[117],"obstacles":[119],"while":[120],"aiming":[121],"reach":[123],"goal":[125,144],"point.":[126],"A":[127],"simple":[131],"convenient":[133],"educational":[135],"purposes,":[136],"since":[137],"outcome":[139],"unambiguous":[141],"reached":[146],"or":[147,152],"not,":[148],"collision":[150],"happened":[151],"not).":[153],"Due":[154],"lack":[157],"open-source":[159,195],"graphical":[160],"simulators":[162],"concerning":[163],"field":[165],"combines":[170],"theoretical":[171],"exposition":[172],"accessible":[175],"practical":[176],"facilitate":[179],"apprehension.":[181],"demonstrated":[184],"are":[185],"produced":[186],"by":[187],"Python":[189],"script":[190],"that":[191],"released":[193],"in":[201,206],"such":[202],"innovative":[203],"research":[204],"topic":[205],"robotics.":[207]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}