{"id":"https://openalex.org/W4402592252","doi":"https://doi.org/10.1109/tai.2024.3433614","title":"Self-Model-Free Learning Versus Learning With External Rewards in Information Constrained Environments","display_name":"Self-Model-Free Learning Versus Learning With External Rewards in Information Constrained Environments","publication_year":2024,"publication_date":"2024-09-18","ids":{"openalex":"https://openalex.org/W4402592252","doi":"https://doi.org/10.1109/tai.2024.3433614"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2024.3433614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3433614","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","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/A5043865100","display_name":"Prachi Pratyusha Sahoo","orcid":"https://orcid.org/0000-0002-2768-601X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prachi Pratyusha Sahoo","raw_affiliation_strings":["Woodruff School for Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA, USA","School for Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA"],"raw_orcid":"https://orcid.org/0000-0002-2768-601X","affiliations":[{"raw_affiliation_string":"Woodruff School for Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School for Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040301558","display_name":"Kyriakos G. Vamvoudakis","orcid":"https://orcid.org/0000-0003-1978-4848"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyriakos G. Vamvoudakis","raw_affiliation_strings":["Daniel H. Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA, USA","School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA"],"raw_orcid":"https://orcid.org/0000-0003-1978-4848","affiliations":[{"raw_affiliation_string":"Daniel H. Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12703849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":"12","first_page":"6566","last_page":"6579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.8763999938964844,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.8763999938964844,"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":0.7940000295639038,"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/T10320","display_name":"Neural Networks and Applications","score":0.762499988079071,"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/computer-science","display_name":"Computer science","score":0.5297784805297852},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38010528683662415},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.34174787998199463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33465927839279175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5297784805297852},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38010528683662415},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34174787998199463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33465927839279175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2024.3433614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3433614","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W36373687","https://openalex.org/W1513689897","https://openalex.org/W1571323288","https://openalex.org/W1742307920","https://openalex.org/W1891098503","https://openalex.org/W1901616594","https://openalex.org/W1985235885","https://openalex.org/W1986495842","https://openalex.org/W2006920079","https://openalex.org/W2012173880","https://openalex.org/W2022406843","https://openalex.org/W2052334067","https://openalex.org/W2057242689","https://openalex.org/W2062175538","https://openalex.org/W2064111006","https://openalex.org/W2108383324","https://openalex.org/W2126881026","https://openalex.org/W2132688659","https://openalex.org/W2139385677","https://openalex.org/W2152161277","https://openalex.org/W2157076370","https://openalex.org/W2168205742","https://openalex.org/W2169239645","https://openalex.org/W2479335603","https://openalex.org/W2528903881","https://openalex.org/W2564717627","https://openalex.org/W2581108373","https://openalex.org/W2740197008","https://openalex.org/W2772589676","https://openalex.org/W2943852008","https://openalex.org/W3012156918","https://openalex.org/W3081103181","https://openalex.org/W3121057473","https://openalex.org/W3182959332","https://openalex.org/W3201699978","https://openalex.org/W4211043782","https://openalex.org/W4214717370","https://openalex.org/W4229706427","https://openalex.org/W4243404706","https://openalex.org/W4294691901","https://openalex.org/W6659680093","https://openalex.org/W6681825124","https://openalex.org/W6736780667","https://openalex.org/W6742461812"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3],"provide":[4],"a":[5,45,52,69,77],"model-free":[6],"reinforcement":[7,15,28,82,89,109],"learning":[8,21],"(RL)":[9],"framework":[10,43],"that":[11,23,72],"relies":[12],"on":[13],"internal":[14],"signals,":[16],"called":[17],"self-model-free":[18],"RL,":[19],"for":[20,57],"agents":[22],"experience":[24],"loss":[25,59,106],"of":[26,33,51,97,117],"the":[27,31,49,74,81,98,108,115,118],"signals":[29,83,90],"in":[30,48,107],"form":[32,50],"packet":[34],"drops":[35],"and/or":[36],"jamming":[37],"attacks":[38],"by":[39],"malicious":[40],"agents.":[41],"The":[42,95],"embeds":[44],"correcting":[46],"mechanism":[47],"goal":[53,78],"network":[54,79],"to":[55],"compensate":[56],"information":[58,105],"and":[60,63],"produce":[61],"optimal":[62],"stabilizing":[64],"policies.":[65],"It":[66],"also":[67],"provides":[68],"trade-off":[70],"scheme":[71],"reconstructs":[73],"reward":[75],"using":[76],"whenever":[80],"are":[84,93],"lost":[85],"but":[86],"utilizes":[87],"true":[88],"when":[91],"they":[92],"available.":[94],"stability":[96],"equilibrium":[99],"point":[100],"is":[101],"guaranteed":[102],"despite":[103],"fractional":[104],"signals.":[110],"Finally,":[111],"simulation":[112],"results":[113],"validate":[114],"efficacy":[116],"proposed":[119],"work.":[120]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}