{"id":"https://openalex.org/W3130800560","doi":"https://doi.org/10.1109/lra.2021.3061397","title":"Adversarial Inverse Reinforcement Learning With Self-Attention Dynamics Model","display_name":"Adversarial Inverse Reinforcement Learning With Self-Attention Dynamics Model","publication_year":2021,"publication_date":"2021-02-23","ids":{"openalex":"https://openalex.org/W3130800560","doi":"https://doi.org/10.1109/lra.2021.3061397","mag":"3130800560"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3061397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3061397","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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/A5101424688","display_name":"Jiankai Sun","orcid":"https://orcid.org/0000-0001-5633-1739"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiankai Sun","raw_affiliation_strings":["Centre for Perceptual and Interactive Intelligence, Hong Kong, China","Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-5633-1739","affiliations":[{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence, Hong Kong, China","institution_ids":[]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068559249","display_name":"Lantao Yu","orcid":"https://orcid.org/0000-0003-0569-952X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lantao Yu","raw_affiliation_strings":["Computer Science Department, Stanford University, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Mountain View, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009286411","display_name":"Pinqian Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pinqian Dong","raw_affiliation_strings":["State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046214073","display_name":"Bo Lu","orcid":"https://orcid.org/0000-0002-2858-1121"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bo Lu","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-2858-1121","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033444412","display_name":"Bolei Zhou","orcid":"https://orcid.org/0000-0003-4030-0684"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bolei Zhou","raw_affiliation_strings":["Centre for Perceptual and Interactive Intelligence, Hong Kong, China","Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-4030-0684","affiliations":[{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence, Hong Kong, China","institution_ids":[]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7308,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.91518461,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"6","issue":"2","first_page":"1880","last_page":"1886"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9805999994277954,"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":0.9760000109672546,"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":0.7910969853401184},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.766472578048706},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7601925134658813},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.7212477922439575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5496712923049927},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5243865847587585},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5002889633178711},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.49392443895339966},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48529165983200073},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.45499947667121887},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.42775338888168335},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4267638921737671},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2754684090614319},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2198081910610199},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1092204749584198}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7910969853401184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766472578048706},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7601925134658813},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.7212477922439575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5496712923049927},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5243865847587585},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5002889633178711},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.49392443895339966},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48529165983200073},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.45499947667121887},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.42775338888168335},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4267638921737671},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2754684090614319},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2198081910610199},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1092204749584198},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2021.3061397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3061397","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1527702126","https://openalex.org/W1771410628","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2119717200","https://openalex.org/W2122262818","https://openalex.org/W2135043890","https://openalex.org/W2140135625","https://openalex.org/W2290104316","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2575705757","https://openalex.org/W2740210681","https://openalex.org/W2890208753","https://openalex.org/W2890803796","https://openalex.org/W2950268955","https://openalex.org/W2952264928","https://openalex.org/W2963091558","https://openalex.org/W2963277051","https://openalex.org/W2963403868","https://openalex.org/W2963508354","https://openalex.org/W2963590100","https://openalex.org/W2963960193","https://openalex.org/W2964006217","https://openalex.org/W2995298643","https://openalex.org/W3090901006","https://openalex.org/W3158726102","https://openalex.org/W3159812837","https://openalex.org/W3208836296","https://openalex.org/W3211174185","https://openalex.org/W4288319859","https://openalex.org/W4298206671","https://openalex.org/W4385245566","https://openalex.org/W6638018090","https://openalex.org/W6639949747","https://openalex.org/W6674884181","https://openalex.org/W6677929280","https://openalex.org/W6680657880","https://openalex.org/W6696380822","https://openalex.org/W6718092244","https://openalex.org/W6729448088","https://openalex.org/W6739901393","https://openalex.org/W6741832191","https://openalex.org/W6751494529","https://openalex.org/W6754184789","https://openalex.org/W6754615820","https://openalex.org/W6764053384","https://openalex.org/W6771217966","https://openalex.org/W6794641712","https://openalex.org/W6803030377"],"related_works":["https://openalex.org/W3013360982","https://openalex.org/W3198184493","https://openalex.org/W2984518291","https://openalex.org/W3159117918","https://openalex.org/W3156291593","https://openalex.org/W2901368259","https://openalex.org/W2919013397","https://openalex.org/W4366250584","https://openalex.org/W4319083788","https://openalex.org/W2964157711"],"abstract_inverted_index":{"In":[0,71],"many":[1],"real-world":[2],"applications":[3],"where":[4],"specifying":[5],"a":[6],"proper":[7],"reward":[8],"function":[9],"is":[10,13,26,48,152],"difficult,":[11],"it":[12],"desirable":[14],"to":[15,39,97],"learn":[16],"policies":[17,134],"from":[18,35],"expert":[19,137],"demonstrations.":[20,36],"Adversarial":[21,55,78],"Inverse":[22,79],"Reinforcement":[23,80],"Learning":[24,81],"(AIRL)":[25],"one":[27],"of":[28,46],"the":[29,40,60,76,93,99,106],"most":[30],"common":[31],"approaches":[32],"for":[33,62,109],"learning":[34,145],"However,":[37],"due":[38],"stochastic":[41],"policy,":[42],"current":[43],"computation":[44,100],"graph":[45,101],"AIRL":[47],"no":[49],"longer":[50],"end-to-end":[51,84,102],"differentiable":[52],"like":[53],"Generative":[54],"Networks":[56],"(GANs),":[57],"resulting":[58],"in":[59,147],"need":[61],"high-variance":[63],"gradient":[64],"estimation":[65],"methods":[66],"and":[67,133],"large":[68],"sample":[69],"size.":[70],"this":[72],"work,":[73],"we":[74],"propose":[75],"Model-based":[77],"(MAIRL),":[82],"an":[83],"model-based":[85],"policy":[86,110],"optimization":[87],"method":[88],"with":[89],"self-attention.":[90],"By":[91],"adopting":[92],"self-attention":[94],"dynamics":[95],"model":[96],"make":[98],"differentiable,":[103],"MAIRL":[104],"has":[105],"low":[107],"variance":[108],"optimization.":[111],"We":[112],"evaluate":[113],"our":[114,126],"approach":[115,127],"thoroughly":[116],"on":[117],"various":[118],"control":[119],"tasks.":[120],"The":[121],"experimental":[122],"results":[123],"show":[124],"that":[125,135],"not":[128],"only":[129],"learns":[130],"near-optimal":[131],"rewards":[132],"match":[136],"behavior":[138],"but":[139],"also":[140],"outperforms":[141],"previous":[142],"inverse":[143],"reinforcement":[144],"algorithms":[146],"real":[148],"robot":[149],"experiments.":[150],"Code":[151],"available":[153],"at":[154],"https://decisionforce.github.io/MAIRL/.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}