{"id":"https://openalex.org/W4383109329","doi":"https://doi.org/10.1109/icra48891.2023.10160557","title":"Explainable Action Advising for Multi-Agent Reinforcement Learning","display_name":"Explainable Action Advising for Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383109329","doi":"https://doi.org/10.1109/icra48891.2023.10160557"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5041892392","display_name":"Yue Guo","orcid":"https://orcid.org/0000-0003-2482-4445"},"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":"Yue Guo","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048453008","display_name":"Joseph Campbell","orcid":"https://orcid.org/0000-0002-7924-8548"},"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":"Joseph Campbell","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048668442","display_name":"Simon Stepputtis","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":"Simon Stepputtis","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101945786","display_name":"Ruiyu Li","orcid":"https://orcid.org/0000-0002-4172-027X"},"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":"Ruiyu Li","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103176418","display_name":"Dana Hughes","orcid":"https://orcid.org/0009-0009-4500-181X"},"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":"Dana Hughes","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061127138","display_name":"Fei Fang","orcid":"https://orcid.org/0000-0003-2256-8329"},"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":"Fei Fang","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087505541","display_name":"Katia Sycara","orcid":"https://orcid.org/0000-0001-5635-1406"},"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":"Katia Sycara","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3053,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84033348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5515","last_page":"5521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9944000244140625,"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":0.7577570676803589},{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.7509772777557373},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7104068398475647},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6854921579360962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6648117303848267},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5668244361877441},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5068374276161194},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.48621121048927307},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4641348719596863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4430273473262787},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4398394525051117},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.35816603899002075},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22506266832351685},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.14157599210739136},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10545164346694946}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7577570676803589},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.7509772777557373},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7104068398475647},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6854921579360962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6648117303848267},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5668244361877441},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5068374276161194},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.48621121048927307},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4641348719596863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4430273473262787},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4398394525051117},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.35816603899002075},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22506266832351685},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.14157599210739136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10545164346694946},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G199976790","display_name":null,"funder_award_id":"HR001120C0036","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1529399279","https://openalex.org/W1794897921","https://openalex.org/W1931877416","https://openalex.org/W2141754131","https://openalex.org/W2563829177","https://openalex.org/W2617547828","https://openalex.org/W2620645529","https://openalex.org/W2735506162","https://openalex.org/W2736601468","https://openalex.org/W2739573821","https://openalex.org/W2739657930","https://openalex.org/W2803974723","https://openalex.org/W2921955147","https://openalex.org/W2963277051","https://openalex.org/W2963363446","https://openalex.org/W2963390684","https://openalex.org/W2963847595","https://openalex.org/W2976108375","https://openalex.org/W2991093017","https://openalex.org/W2996868001","https://openalex.org/W3003498399","https://openalex.org/W3037582147","https://openalex.org/W3173894685","https://openalex.org/W3174394955","https://openalex.org/W3194138753","https://openalex.org/W3210485068","https://openalex.org/W3213112773","https://openalex.org/W4214717370","https://openalex.org/W4243420394","https://openalex.org/W4246078117","https://openalex.org/W4310747546","https://openalex.org/W4313351098","https://openalex.org/W4320082628","https://openalex.org/W6631533588","https://openalex.org/W6640174482","https://openalex.org/W6680829273","https://openalex.org/W6718092244","https://openalex.org/W6741002519","https://openalex.org/W6741054924","https://openalex.org/W6748314335","https://openalex.org/W6751437432","https://openalex.org/W6771007510","https://openalex.org/W6780070463","https://openalex.org/W6790415032","https://openalex.org/W6793862206","https://openalex.org/W6800001885","https://openalex.org/W6802732210"],"related_works":["https://openalex.org/W3090906284","https://openalex.org/W253876680","https://openalex.org/W1987931999","https://openalex.org/W2920061524","https://openalex.org/W4293797372","https://openalex.org/W4238052600","https://openalex.org/W4310083477","https://openalex.org/W3005176110","https://openalex.org/W162918864","https://openalex.org/W2501594388"],"abstract_inverted_index":{"Action":[0,66],"advising":[1],"is":[2,38,116,124],"a":[3,21],"knowledge":[4],"transfer":[5],"technique":[6],"for":[7,52],"reinforcement":[8],"learning":[9,107],"based":[10],"on":[11,92],"the":[12,29,42,53,70,82,88,114],"teacher-student":[13],"paradigm.":[14],"An":[15],"expert":[16],"teacher":[17,71,115],"provides":[18,72],"advice":[19,37,74,98],"to":[20,27,55,60,90,102,141],"student":[22,54,89],"during":[23],"training":[24],"in":[25,41,68,111,126],"order":[26],"improve":[28],"student's":[30],"sample":[31,104],"efficiency":[32,105],"and":[33,58,100,106,129,136],"policy":[34,134],"performance.":[35],"Such":[36],"commonly":[39],"given":[40],"form":[43],"of":[44],"state-action":[45],"pairs.":[46],"However,":[47],"it":[48,50,94],"makes":[49],"difficult":[51],"reason":[56],"with":[57],"apply":[59],"novel":[61],"states.":[62],"We":[63,118],"introduce":[64],"Explainable":[65],"Advising,":[67],"which":[69],"action":[73,83],"as":[75,77],"well":[76],"associated":[78],"explanations":[79],"indicating":[80],"why":[81],"was":[84],"chosen.":[85],"This":[86],"allows":[87],"self-reflect":[91],"what":[93],"has":[95],"learned,":[96],"enabling":[97],"generalization":[99],"leading":[101],"improved":[103,133],"performance":[108],"-":[109],"even":[110],"environments":[112],"where":[113],"sub-optimal.":[117],"empirically":[119],"show":[120],"that":[121],"our":[122],"framework":[123],"effective":[125],"both":[127],"single-agent":[128],"multi-agent":[130],"scenarios,":[131],"yielding":[132],"returns":[135],"convergence":[137],"rates":[138],"when":[139],"compared":[140],"state-of-the-art":[142],"methods.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}