{"id":"https://openalex.org/W7204863525","doi":"https://doi.org/10.5281/zenodo.22235153","title":"Rewards, Regrets, and Rubber Arms: A Critical Survey Review of Reinforcement Learning in Games and Robotics","display_name":"Rewards, Regrets, and Rubber Arms: A Critical Survey Review of Reinforcement Learning in Games and Robotics","publication_year":2026,"publication_date":"2026-09-01","ids":{"openalex":"https://openalex.org/W7204863525","doi":"https://doi.org/10.5281/zenodo.22235153"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22235153","doi":"https://doi.org/10.5281/zenodo.22235153","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22235153","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22235153","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120933120","display_name":"Zen Revista","orcid":"https://orcid.org/0009-0007-6299-2008","observed_orcids":["https://orcid.org/0009-0007-6299-2008"]},"institutions":[{"id":"https://openalex.org/I4210124990","display_name":"Faculdades Guarulhos","ror":"https://ror.org/02s6maw65","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210124990"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Revista, Zen","raw_affiliation_strings":["Faculdade de Guarulhos (FG)"],"raw_orcid":"https://orcid.org/0009-0007-6299-2008","affiliations":[{"raw_affiliation_string":"Faculdade de Guarulhos (FG)","institution_ids":["https://openalex.org/I4210124990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148850874","display_name":"10 IA","orcid":"https://orcid.org/0009-0007-6299-2008","observed_orcids":["https://orcid.org/0009-0007-6299-2008"]},"institutions":[{"id":"https://openalex.org/I4210124990","display_name":"Faculdades Guarulhos","ror":"https://ror.org/02s6maw65","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210124990"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"IA, 10","raw_affiliation_strings":["Faculdade de Guarulhos (FG)"],"raw_orcid":"https://orcid.org/0009-0007-6299-2008","affiliations":[{"raw_affiliation_string":"Faculdade de Guarulhos (FG)","institution_ids":["https://openalex.org/I4210124990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210124990"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11574","display_name":"Artificial Intelligence in Games","score":9.999999747378752e-05,"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/T13904","display_name":"Artificial Intelligence Applications","score":9.999999747378752e-05,"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":0.9559999704360962},{"id":"https://openalex.org/keywords/game-theory","display_name":"game theory","score":0.4779999852180481},{"id":"https://openalex.org/keywords/robotics","display_name":"robotics","score":0.8550000190734863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"artificial intelligence","score":0.5239999890327454},{"id":"https://openalex.org/keywords/evidence-synthesis","display_name":"evidence synthesis","score":0.3540000021457672},{"id":"https://openalex.org/keywords/methodological-pluralism","display_name":"methodological pluralism","score":0.871999979019165},{"id":"https://openalex.org/keywords/cumulative-research","display_name":"cumulative research","score":0.35899999737739563},{"id":"https://openalex.org/keywords/publication-practices","display_name":"publication practices","score":0.6069999933242798},{"id":"https://openalex.org/keywords/research-traditions","display_name":"research traditions","score":0.41200000047683716},{"id":"https://openalex.org/keywords/conceptual-debates","display_name":"conceptual debates","score":0.4050000011920929},{"id":"https://openalex.org/keywords/integrative-research-design","display_name":"integrative research design","score":0.5630000233650208}],"concepts":[{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5920000076293945},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.517300009727478},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4927999973297119},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.41029998660087585},{"id":"https://openalex.org/C2778360550","wikidata":"https://www.wikidata.org/wiki/Q249542","display_name":"Transdisciplinarity","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.39980000257492065},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.38830000162124634},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C14224292","wikidata":"https://www.wikidata.org/wiki/Q13600188","display_name":"Conceptual framework","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C44725695","wikidata":"https://www.wikidata.org/wiki/Q288156","display_name":"Normative","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3327000141143799},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.31470000743865967},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.31200000643730164},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C48164120","wikidata":"https://www.wikidata.org/wiki/Q4491893","display_name":"Concept learning","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2703999876976013},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26089999079704285},{"id":"https://openalex.org/C49831778","wikidata":"https://www.wikidata.org/wiki/Q879021","display_name":"Pluralism (philosophy)","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.5281/zenodo.22235153","doi":"https://doi.org/10.5281/zenodo.22235153","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22235153","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.5281/zenodo.22235154","doi":"https://doi.org/10.5281/zenodo.22235154","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22235154","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.5281/zenodo.22313708","doi":"https://doi.org/10.5281/zenodo.22313708","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22313708","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.5281/zenodo.22313709","doi":"https://doi.org/10.5281/zenodo.22313709","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22313709","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.5281/zenodo.22637824","doi":"https://doi.org/10.5281/zenodo.22637824","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22637824","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.5281/zenodo.22637825","doi":"https://doi.org/10.5281/zenodo.22637825","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22637825","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22235153","doi":"https://doi.org/10.5281/zenodo.22235153","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22235153","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7206203210","https://openalex.org/W7206184659","https://openalex.org/W7206171471","https://openalex.org/W7204850019","https://openalex.org/W7214307436","https://openalex.org/W7204714089","https://openalex.org/W6968643226","https://openalex.org/W7203792021","https://openalex.org/W7214316604","https://openalex.org/W3196579419"],"abstract_inverted_index":{"This":[0],"article":[1,193],"presents":[2],"a":[3,143,147,198,204],"narrative":[4],"review":[5,50,124],"of":[6,16,46,55,74,98,154,160,182],"Reinforcement":[7],"Learning":[8],"in":[9,13,208],"Games":[10],"and":[11,37,62,69,83,101,106,149,179,184,203],"Robotics":[12],"the":[14,49,52,56,59,71,77,84,96,108,129,150,155,158,180],"context":[15],"Artificial":[17,209],"Intelligence.":[18,210],"The":[19,123,192],"literature":[20,130],"on":[21,42,187],"this":[22],"topic":[23,156],"has":[24],"expanded":[25],"substantially":[26],"over":[27],"recent":[28],"decades,":[29],"yet":[30],"it":[31],"remains":[32],"fragmented":[33],"across":[34],"subfields,":[35],"methods,":[36],"national":[38],"research":[39,115,174],"traditions.":[40],"Drawing":[41],"an":[43],"interpretive":[44],"synthesis":[45,177],"representative":[47],"contributions,":[48],"reconstructs":[51],"historical":[53],"development":[54],"area,":[57],"examines":[58],"conceptual":[60,163],"foundations":[61],"definitional":[63,183],"disputes":[64],"that":[65,87],"organize":[66],"its":[67,161],"debates,":[68],"maps":[70],"contemporary":[72],"landscape":[73],"research,":[75],"including":[76],"methodological":[78,137],"shift":[79],"toward":[80],"data-intensive":[81],"approaches":[82],"institutional":[85],"pressures":[86],"shape":[88],"publication":[89],"practice.":[90],"Particular":[91],"attention":[92],"is":[93,131,139,170,194],"given":[94],"to":[95,107],"role":[97],"reinforcement":[99],"learning":[100],"robotics":[102],"as":[103,142,146,196],"organizing":[104],"themes,":[105],"conditions":[109],"under":[110],"which":[111,188],"findings":[112],"from":[113],"different":[114],"traditions":[116],"can":[117],"be":[118],"brought":[119],"into":[120],"productive":[121],"comparison.":[122],"identifies":[125],"three":[126],"synthetic":[127],"conclusions:":[128],"cumulatively":[132],"strong":[133],"but":[134],"organizationally":[135],"weak;":[136],"pluralism":[138],"better":[140],"understood":[141],"resource":[144],"than":[145],"defect;":[148],"growing":[151],"practical":[152],"salience":[153],"raises":[157],"stakes":[159],"unresolved":[162],"questions.":[164],"An":[165],"agenda":[166],"for":[167,201,206],"future":[168],"work":[169,186],"proposed,":[171],"emphasizing":[172],"integrative":[173],"designs,":[175],"transparent":[176],"practices,":[178],"protection":[181],"infrastructural":[185],"cumulative":[189],"progress":[190],"depends.":[191],"intended":[195],"both":[197],"reference":[199],"map":[200],"newcomers":[202],"provocation":[205],"specialists":[207]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-02T00:00:00"}
