{"id":"https://openalex.org/W3207459740","doi":"https://doi.org/10.2478/jagi-2022-0001","title":"Extending Environments to Measure Self-reflection in Reinforcement Learning","display_name":"Extending Environments to Measure Self-reflection in Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W3207459740","doi":"https://doi.org/10.2478/jagi-2022-0001","mag":"3207459740"},"language":"en","primary_location":{"id":"doi:10.2478/jagi-2022-0001","is_oa":true,"landing_page_url":"https://doi.org/10.2478/jagi-2022-0001","pdf_url":"https://sciendo.com/pdf/10.2478/jagi-2022-0001","source":{"id":"https://openalex.org/S4210180872","display_name":"Journal of Artificial General Intelligence","issn_l":"1946-0163","issn":["1946-0163"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial General Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://sciendo.com/pdf/10.2478/jagi-2022-0001","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016012515","display_name":"Samuel Allen Alexander","orcid":"https://orcid.org/0000-0002-7930-110X"},"institutions":[{"id":"https://openalex.org/I1313313744","display_name":"United States Securities and Exchange Commission","ror":"https://ror.org/01xqwbk25","country_code":"US","type":"government","lineage":["https://openalex.org/I1313313744"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Samuel Allen Alexander","raw_affiliation_strings":["The U.S. Securities and Exchange Commission"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The U.S. Securities and Exchange Commission","institution_ids":["https://openalex.org/I1313313744"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050139515","display_name":"Michael Castaneda","orcid":null},"institutions":[{"id":"https://openalex.org/I42387498","display_name":"Knox College","ror":"https://ror.org/04hfkdb50","country_code":"US","type":"education","lineage":["https://openalex.org/I42387498"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Castaneda","raw_affiliation_strings":["KX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KX","institution_ids":["https://openalex.org/I42387498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058927842","display_name":"Kevin Compher","orcid":null},"institutions":[{"id":"https://openalex.org/I38260057","display_name":"In-Q-Tel","ror":"https://ror.org/02qp5k481","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I38260057"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Compher","raw_affiliation_strings":["InQTel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"InQTel","institution_ids":["https://openalex.org/I38260057"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017161602","display_name":"Oscar E. Mart\u00ednez","orcid":"https://orcid.org/0000-0002-7034-4891"},"institutions":[{"id":"https://openalex.org/I1313313744","display_name":"United States Securities and Exchange Commission","ror":"https://ror.org/01xqwbk25","country_code":"US","type":"government","lineage":["https://openalex.org/I1313313744"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oscar Martinez","raw_affiliation_strings":["The U.S. Securities and Exchange Commission"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The U.S. Securities and Exchange Commission","institution_ids":["https://openalex.org/I1313313744"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016012515"],"corresponding_institution_ids":["https://openalex.org/I1313313744"],"apc_list":null,"apc_paid":null,"fwci":1.8284,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86458752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"13","issue":"1","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.98089998960495,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9689000248908997,"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":0.813785195350647},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.7333962917327881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7079629898071289},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.6987656354904175},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6643491387367249},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.612752377986908},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5737455487251282},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5693078637123108},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.5366122126579285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35484778881073},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17232045531272888},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07074415683746338},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.059375613927841187},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.05545845627784729}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.813785195350647},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.7333962917327881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7079629898071289},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.6987656354904175},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6643491387367249},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.612752377986908},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5737455487251282},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5693078637123108},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.5366122126579285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35484778881073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17232045531272888},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07074415683746338},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.059375613927841187},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.05545845627784729},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.2478/jagi-2022-0001","is_oa":true,"landing_page_url":"https://doi.org/10.2478/jagi-2022-0001","pdf_url":"https://sciendo.com/pdf/10.2478/jagi-2022-0001","source":{"id":"https://openalex.org/S4210180872","display_name":"Journal of Artificial General Intelligence","issn_l":"1946-0163","issn":["1946-0163"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial General Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:philarchive.org/rec/ALEEET-3","is_oa":true,"landing_page_url":"https://philarchive.org/rec/ALEEET-3","pdf_url":"https://philpapers.org/archive/ALEEET-3.pdf","source":{"id":"https://openalex.org/S4306402130","display_name":"PhilPapers (PhilPapers Foundation)","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":"info:eu-repo/semantics/article"},{"id":"pmh:oai:philpapers.org/rec/ALEEET-3","is_oa":false,"landing_page_url":"https://philpapers.org/rec/ALEEET-3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402131","display_name":"PhilPapers (PhilPapers Foundation)","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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.2478/jagi-2022-0001","is_oa":true,"landing_page_url":"https://doi.org/10.2478/jagi-2022-0001","pdf_url":"https://sciendo.com/pdf/10.2478/jagi-2022-0001","source":{"id":"https://openalex.org/S4210180872","display_name":"Journal of Artificial General Intelligence","issn_l":"1946-0163","issn":["1946-0163"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial General Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3207459740.pdf","grobid_xml":"https://content.openalex.org/works/W3207459740.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1553200036","https://openalex.org/W1575020259","https://openalex.org/W1638203394","https://openalex.org/W1790098863","https://openalex.org/W1935023620","https://openalex.org/W2013391942","https://openalex.org/W2084751229","https://openalex.org/W2101493843","https://openalex.org/W2114690085","https://openalex.org/W2117703827","https://openalex.org/W2144372853","https://openalex.org/W2145339207","https://openalex.org/W2150451941","https://openalex.org/W2150468603","https://openalex.org/W2337523958","https://openalex.org/W2396961959","https://openalex.org/W2582697902","https://openalex.org/W2774485744","https://openalex.org/W2796979132","https://openalex.org/W2905631704","https://openalex.org/W2948625193","https://openalex.org/W2963060032","https://openalex.org/W2963241009","https://openalex.org/W2963505878","https://openalex.org/W2973515080","https://openalex.org/W2989818084","https://openalex.org/W2994073215","https://openalex.org/W3034946435","https://openalex.org/W3101697293","https://openalex.org/W3103780890","https://openalex.org/W3164005523","https://openalex.org/W3201764368","https://openalex.org/W3212045844","https://openalex.org/W4206804229","https://openalex.org/W4225425442","https://openalex.org/W4315798512","https://openalex.org/W6640399833","https://openalex.org/W6681355956","https://openalex.org/W6769679262","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2089013912","https://openalex.org/W2076061571","https://openalex.org/W1987513656","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Abstract":[0],"We":[1,90],"consider":[2],"an":[3,46,87],"extended":[4,56,76,94,116],"notion":[5],"of":[6,72,83,93,115],"reinforcement":[7],"learning":[8],"in":[9,111],"which":[10,101],"the":[11,15,22,36,62,70],"environment":[12],"can":[13],"simulate":[14],"agent":[16,47,63,88],"and":[17,96],"base":[18],"its":[19],"outputs":[20,38],"on":[21],"agent\u2019s":[23],"hypothetical":[24],"behavior.":[25],"Since":[26],"good":[27,51],"performance":[28,52,68,110],"usually":[29],"requires":[30],"paying":[31],"attention":[32],"to":[33,48,64,104],"whatever":[34],"things":[35],"environment\u2019s":[37],"are":[39],"based":[40],"on,":[41],"we":[42],"argue":[43],"that":[44],"for":[45,61],"achieve":[49],"on-average":[50],"across":[53],"many":[54],"such":[55],"environments,":[57],"it":[58],"is":[59],"necessary":[60],"self-reflect.":[65],"Thus":[66],"weighted-average":[67],"over":[69],"space":[71],"all":[73],"suitably":[74],"well-behaved":[75],"environments":[77,95],"could":[78],"be":[79],"considered":[80],"a":[81,98,112],"way":[82],"measuring":[84],"how":[85],"self-reflective":[86],"is.":[89],"give":[91],"examples":[92],"introduce":[97],"simple":[99],"transformation":[100],"experimentally":[102],"seems":[103],"increase":[105],"some":[106],"standard":[107],"RL":[108],"agents\u2019":[109],"certain":[113],"type":[114],"environment.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-01T06:04:38.248271","created_date":"2025-10-10T00:00:00"}