{"id":"https://openalex.org/W4391827290","doi":"https://doi.org/10.1109/lra.2024.3366023","title":"SC-AIRL: Share-Critic in Adversarial Inverse Reinforcement Learning for Long-Horizon Task","display_name":"SC-AIRL: Share-Critic in Adversarial Inverse Reinforcement Learning for Long-Horizon Task","publication_year":2024,"publication_date":"2024-02-14","ids":{"openalex":"https://openalex.org/W4391827290","doi":"https://doi.org/10.1109/lra.2024.3366023"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3366023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3366023","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5108984619","display_name":"Guangyu Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guangyu Xiang","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057147579","display_name":"Shaodong Li","orcid":"https://orcid.org/0000-0002-5034-8721"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaodong Li","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062793914","display_name":"Feng Shuang","orcid":"https://orcid.org/0000-0002-4733-4732"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Shuang","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006605583","display_name":"Fang Gao","orcid":"https://orcid.org/0000-0003-1816-5420"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Gao","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101903766","display_name":"Xiaogang Yuan","orcid":"https://orcid.org/0009-0003-3842-2807"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaogang Yuan","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5108984619"],"corresponding_institution_ids":["https://openalex.org/I150807315"],"apc_list":null,"apc_paid":null,"fwci":2.155,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88300853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"9","issue":"4","first_page":"3179","last_page":"3186"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.987500011920929,"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":0.7669331431388855},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7451434135437012},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6889801621437073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6655848026275635},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6539618968963623},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5757002830505371},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5240728259086609},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.5063599348068237},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4727174639701843},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44252991676330566},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43956080079078674},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1242816150188446},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0928424596786499},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07043617963790894}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7669331431388855},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7451434135437012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6889801621437073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6655848026275635},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6539618968963623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5757002830505371},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5240728259086609},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5063599348068237},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4727174639701843},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44252991676330566},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43956080079078674},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1242816150188446},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0928424596786499},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07043617963790894},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3366023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3366023","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1527702126","https://openalex.org/W2300445845","https://openalex.org/W2566467060","https://openalex.org/W2604847142","https://openalex.org/W2736601468","https://openalex.org/W2963099939","https://openalex.org/W2963678934","https://openalex.org/W3012366945","https://openalex.org/W3018036994","https://openalex.org/W3129322645","https://openalex.org/W3130800560","https://openalex.org/W4316021894","https://openalex.org/W4320008850","https://openalex.org/W4360584414","https://openalex.org/W4383108457","https://openalex.org/W4386090379","https://openalex.org/W6638018090","https://openalex.org/W6674884181","https://openalex.org/W6683397050","https://openalex.org/W6696380822","https://openalex.org/W6717230150","https://openalex.org/W6718092244","https://openalex.org/W6731259203","https://openalex.org/W6738261575","https://openalex.org/W6741002519","https://openalex.org/W6745347688","https://openalex.org/W6748523217","https://openalex.org/W6753960536","https://openalex.org/W6754484421","https://openalex.org/W6754848371","https://openalex.org/W6760439459","https://openalex.org/W6769035977","https://openalex.org/W6779830607","https://openalex.org/W6794641712","https://openalex.org/W6797377937","https://openalex.org/W6803030377","https://openalex.org/W6849708406","https://openalex.org/W6854929498"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2368605798"],"abstract_inverted_index":{"Adversarial":[0],"Inverse":[1],"Reinforcement":[2],"Learning":[3],"(AIRL)":[4],"has":[5],"gained":[6],"popularity":[7],"as":[8],"an":[9,160,164],"alternative":[10],"to":[11,33,57,63,66,69,77,137,173],"supervised":[12],"imitation":[13],"learning,":[14],"addressing":[15],"the":[16,21,34,59,70,86,98,133,168,171,178,183],"distributional":[17],"bias":[18],"issue":[19],"of":[20,36,170,180],"latter.":[22],"However,":[23],"it":[24],"still":[25],"faces":[26],"significant":[27],"challenges":[28],"in":[29,145],"long-horizon":[30,91],"tasks":[31,92,149,176],"due":[32,62],"lack":[35],"effective":[37],"exploration.":[38,103],"In":[39],"our":[40,154],"letter,":[41],"we":[42,84,126,158],"demonstrate":[43,150],"that":[44,151],"standard":[45],"AIRL":[46],"strategies":[47],"end":[48],"exploration":[49,139],"prematurely":[50],"during":[51,132],"online":[52],"reinforcement":[53],"learning":[54,135],"and":[55,112,117,163,177],"fail":[56],"learn":[58],"entire":[60],"task":[61],"their":[64],"inability":[65],"fully":[67],"conform":[68],"expert":[71,106],"distribution,":[72],"which":[73,96],"is":[74],"particularly":[75],"detrimental":[76],"real-world":[78],"robots.":[79],"To":[80],"address":[81],"these":[82],"challenges,":[83],"introduce":[85],"SC-AIRL":[87,104,152,181],"approach.":[88],"It":[89],"decomposes":[90],"into":[93],"logical":[94],"subtasks":[95,111],"reduces":[97],"agent's":[99],"need":[100],"for":[101,108],"rich":[102],"utilizes":[105],"demonstrations":[107],"performing":[109],"multiple":[110],"shares":[113],"a":[114,128],"single":[115],"critic":[116],"identical":[118],"reward":[119],"function":[120],"across":[121],"different":[122],"subtask":[123,134],"trainings.":[124],"Additionally,":[125],"incorporate":[127],"human":[129],"intervention":[130],"mechanism":[131],"process":[136],"keep":[138],"from":[140],"ending":[141],"prematurely.":[142],"Our":[143],"experiments":[144],"challenging":[146],"robot":[147],"manipulation":[148],"outperforms":[153],"baselines":[155],"significantly.":[156],"Furthermore,":[157],"conduct":[159],"exploratory":[161],"experiment":[162],"empirical":[165],"analysis,":[166],"emphasizing":[167],"potential":[169],"model":[172],"manage":[174],"complex":[175],"advantages":[179],"over":[182],"baseline,":[184],"respectively.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}