{"id":"https://openalex.org/W7138945601","doi":"https://doi.org/10.1609/aaai.v40i48.42261","title":"Memory Based Advantage Shaping for LLM-Guided Reinforcement Learning (Student Abstract)","display_name":"Memory Based Advantage Shaping for LLM-Guided Reinforcement Learning (Student Abstract)","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138945601","doi":"https://doi.org/10.1609/aaai.v40i48.42261"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i48.42261","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i48.42261","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42261/46222","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42261/46222","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093835444","display_name":"Narjes Nourzad","orcid":"https://orcid.org/0009-0008-6315-8282"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Narjes Nourzad","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108972429","display_name":"Carlee Joe-Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlee Joe-Wong","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22043975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"48","first_page":"41337","last_page":"41339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5105999708175659,"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":0.5105999708175659,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.18209999799728394,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03220000118017197,"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":0.7760999798774719},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.63919997215271},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6069999933242798},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5898000001907349},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.49939998984336853},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45809999108314514},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.41280001401901245}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7760999798774719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365000247955322},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.63919997215271},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6069999933242798},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5898000001907349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5845000147819519},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5547000169754028},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.49939998984336853},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.39579999446868896},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i48.42261","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i48.42261","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42261/46222","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/42261","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/42261","pdf_url":null,"source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i48.42261","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i48.42261","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42261/46222","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138945601.pdf","grobid_xml":"https://content.openalex.org/works/W7138945601.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"environments":[1,139],"with":[2,97,110,153],"sparse":[3],"or":[4],"delayed":[5],"rewards,":[6],"reinforcement":[7],"learning":[8,147],"(RL)":[9],"incurs":[10],"high":[11],"sample":[12,142],"complexity":[13],"due":[14],"to":[15,149,157],"the":[16,28,76,93,104,108,115],"large":[17,31],"number":[18],"of":[19,30],"interactions":[20],"needed":[21],"for":[22,35],"learning.":[23],"This":[24,101],"limitation":[25],"has":[26],"motivated":[27],"use":[29],"language":[32],"models":[33],"(LLMs)":[34],"subgoal":[36],"discovery":[37],"and":[38,55,69,75,124,144],"trajectory":[39],"guidance.":[40],"While":[41],"LLMs":[42],"can":[43],"support":[44],"exploration,":[45],"frequent":[46,161],"reliance":[47],"on":[48,121,131],"LLM":[49,73,133,162],"calls":[50],"raises":[51],"concerns":[52],"about":[53],"scalability":[54],"reliability.":[56],"We":[57],"address":[58],"these":[59],"challenges":[60],"by":[61],"constructing":[62],"a":[63,86],"memory":[64],"graph":[65],"that":[66,89,159],"encodes":[67],"subgoals":[68],"trajectories":[70,95],"from":[71],"both":[72],"guidance":[74,112],"agent\u2019s":[77,94],"own":[78],"successful":[79,99],"rollouts.":[80],"From":[81],"this":[82],"graph,":[83],"we":[84],"derive":[85],"utility":[87,102],"function":[88],"evaluates":[90],"how":[91],"closely":[92],"align":[96],"prior":[98],"strategies.":[100],"shapes":[103],"advantage":[105],"function,":[106],"providing":[107],"critic":[109],"additional":[111],"without":[113],"altering":[114],"reward.":[116],"Our":[117],"method":[118],"relies":[119],"primarily":[120],"offline":[122],"input":[123],"only":[125],"occasional":[126],"online":[127],"queries,":[128],"avoiding":[129],"dependence":[130],"continuous":[132],"supervision.":[134],"Preliminary":[135],"experiments":[136],"in":[137],"benchmark":[138],"show":[140],"improved":[141],"efficiency":[143],"faster":[145],"early":[146],"compared":[148],"baseline":[150],"RL":[151],"methods,":[152],"final":[154],"returns":[155],"comparable":[156],"methods":[158],"require":[160],"interaction.":[163]},"counts_by_year":[],"updated_date":"2026-09-03T10:48:47.769340","created_date":"2026-03-20T00:00:00"}