{"id":"https://openalex.org/W7123342958","doi":"https://doi.org/10.1109/cdc57313.2025.11312643","title":"Model Selection for Inverse Reinforcement Learning via Structural Risk Minimization","display_name":"Model Selection for Inverse Reinforcement Learning via Structural Risk Minimization","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123342958","doi":"https://doi.org/10.1109/cdc57313.2025.11312643"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","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/A5041653678","display_name":"Chendi Qu","orcid":"https://orcid.org/0009-0006-8791-085X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chendi Qu","raw_affiliation_strings":["Shanghai Jiao Tong University,The Dept. of Automation,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,The Dept. of Automation,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004668792","display_name":"Jianping He","orcid":"https://orcid.org/0000-0002-6253-7802"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping He","raw_affiliation_strings":["Shanghai Jiao Tong University,The Dept. of Automation,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,The Dept. of Automation,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122900241","display_name":"Xiaoming Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Duan","raw_affiliation_strings":["Shanghai Jiao Tong University,The Dept. of Automation,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,The Dept. of Automation,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101755165","display_name":"Qi Ye","orcid":"https://orcid.org/0000-0001-7352-548X"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiming Chen","raw_affiliation_strings":["Zhejiang University,The State Key Laboratory of Industrial Control Technology,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,The State Key Laboratory of Industrial Control Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492","https://openalex.org/I4391767838"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041653678"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86333487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6150","last_page":"6155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.785099983215332,"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":0.785099983215332,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.017400000244379044,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.011699999682605267,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7124999761581421},{"id":"https://openalex.org/keywords/empirical-risk-minimization","display_name":"Empirical risk minimization","score":0.5837000012397766},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.5773000121116638},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.546999990940094},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5428000092506409},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5303000211715698},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5192000269889832},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5145999789237976}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7124999761581421},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.5837000012397766},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5773000121116638},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5480999946594238},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5184999704360962},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3935000002384186},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.36090001463890076},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C2779915298","wikidata":"https://www.wikidata.org/wiki/Q7604400","display_name":"Statistical learning theory","level":3,"score":0.32679998874664307},{"id":"https://openalex.org/C154507838","wikidata":"https://www.wikidata.org/wiki/Q7625053","display_name":"Structural risk minimization","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31439998745918274},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27630001306533813},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.518722653388977}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Inverse":[0],"reinforcement":[1],"learning":[2,138],"(IRL)":[3],"usually":[4],"assumes":[5],"the":[6,20,47,69,77,111,118,123,130,147,151,158],"reward":[7,33,90],"function":[8,134],"model":[9,34,41,51,70,91],"is":[10,35,42,140],"pre-specified":[11],"as":[12,117,129],"a":[13,31,50,93],"weighted":[14,153],"sum":[15,154],"of":[16,126,162],"features":[17,28],"and":[18,29,37,60,100,121,160],"estimates":[19],"weighting":[21],"parameters":[22],"only.":[23],"However,":[24],"how":[25],"to":[26,45,56],"select":[27],"determine":[30],"proper":[32],"nontrivial":[36],"experience-dependent.":[38],"A":[39],"simplistic":[40],"less":[43],"likely":[44],"explain":[46],"intention,":[48],"while":[49],"with":[52],"high":[53],"complexity":[54,128],"leads":[55],"substantial":[57],"computation":[58],"cost":[59],"potential":[61],"overfitting.":[62],"This":[63],"paper":[64],"addresses":[65],"this":[66],"trade-off":[67],"in":[68],"selection":[71],"for":[72,107,132,150],"IRL":[73],"problems":[74],"by":[75],"introducing":[76],"structural":[78],"risk":[79],"minimization":[80],"(SRM)":[81],"framework":[82],"from":[83,92,114],"statistical":[84],"learning.":[85],"SRM":[86,105,137],"selects":[87],"an":[88,104],"optimal":[89],"hypothesis":[94,133],"set":[95],"minimizing":[96],"both":[97],"estimation":[98],"error":[99],"complexity.":[101],"To":[102],"formulate":[103],"scheme":[106],"IRL,":[108],"we":[109,145],"estimate":[110],"policy":[112],"gradient":[113],"given":[115],"demonstration":[116],"empirical":[119],"risk,":[120],"establish":[122],"upper":[124],"bound":[125],"Rademacher":[127],"penalty":[131],"classes.":[135],"The":[136],"guarantee":[139],"further":[141],"presented.":[142],"In":[143],"particular,":[144],"provide":[146],"explicit":[148],"form":[149],"linear":[152],"setting.":[155],"Simulations":[156],"demonstrate":[157],"performance":[159],"efficiency":[161],"our":[163],"algorithm.":[164]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-14T00:00:00"}