{"id":"https://openalex.org/W4312871112","doi":"https://doi.org/10.1109/icpr56361.2022.9956245","title":"Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning","display_name":"Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312871112","doi":"https://doi.org/10.1109/icpr56361.2022.9956245"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956245","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102248412","display_name":"Yuansheng Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuansheng Xie","raw_affiliation_strings":["Dartmouth College,Department of Computer Science,Hanover,NH,03755"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dartmouth College,Department of Computer Science,Hanover,NH,03755","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035399743","display_name":"Soroush Vosoughi","orcid":"https://orcid.org/0000-0002-2564-8909"},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soroush Vosoughi","raw_affiliation_strings":["Dartmouth College,Department of Computer Science,Hanover,NH,03755"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dartmouth College,Department of Computer Science,Hanover,NH,03755","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051476268","display_name":"Saeed Hassanpour","orcid":"https://orcid.org/0000-0001-9460-6414"},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saeed Hassanpour","raw_affiliation_strings":["Dartmouth College,Department of Computer Science,Hanover,NH,03755"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dartmouth College,Department of Computer Science,Hanover,NH,03755","institution_ids":["https://openalex.org/I107672454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I107672454"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5067","last_page":"5074"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","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":0.9965000152587891,"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":0.9866999983787537,"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":0.8853297233581543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7005169987678528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6630873680114746},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5883886814117432},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45836126804351807},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11744070053100586}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8853297233581543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7005169987678528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6630873680114746},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5883886814117432},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45836126804351807},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11744070053100586},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956245","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1787224781","https://openalex.org/W1986014385","https://openalex.org/W2064675550","https://openalex.org/W2093647425","https://openalex.org/W2097310377","https://openalex.org/W2106100979","https://openalex.org/W2119567691","https://openalex.org/W2154652894","https://openalex.org/W2168629132","https://openalex.org/W2282821441","https://openalex.org/W2590082389","https://openalex.org/W2594633041","https://openalex.org/W2605409611","https://openalex.org/W2606462007","https://openalex.org/W2753088790","https://openalex.org/W2794518994","https://openalex.org/W2807807246","https://openalex.org/W2809925683","https://openalex.org/W2888487581","https://openalex.org/W2937307539","https://openalex.org/W2943201207","https://openalex.org/W2945976633","https://openalex.org/W2949615363","https://openalex.org/W2952401711","https://openalex.org/W2952561542","https://openalex.org/W2953073956","https://openalex.org/W2962862931","https://openalex.org/W2963292722","https://openalex.org/W2963508354","https://openalex.org/W2966831185","https://openalex.org/W2981731882","https://openalex.org/W3007759824","https://openalex.org/W3034999214","https://openalex.org/W3045376070","https://openalex.org/W3081056513","https://openalex.org/W3093687066","https://openalex.org/W3101609372","https://openalex.org/W3187844553","https://openalex.org/W4229080094","https://openalex.org/W4281295366","https://openalex.org/W4281786453","https://openalex.org/W4288089799","https://openalex.org/W4289543323","https://openalex.org/W4293861706","https://openalex.org/W4298061300","https://openalex.org/W4308235812","https://openalex.org/W6632455782","https://openalex.org/W6682631176","https://openalex.org/W6733905848","https://openalex.org/W6734194636","https://openalex.org/W6736518430","https://openalex.org/W6737947904","https://openalex.org/W6739575509","https://openalex.org/W6744361522","https://openalex.org/W6745347688","https://openalex.org/W6748218292","https://openalex.org/W6752087564","https://openalex.org/W6753870404","https://openalex.org/W6754669440","https://openalex.org/W6764360053","https://openalex.org/W6769311223","https://openalex.org/W6769627184","https://openalex.org/W6773829392","https://openalex.org/W6958966434"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Artificial":[0],"Intelligence,":[1],"particularly":[2],"through":[3],"recent":[4],"advancements":[5],"in":[6,14,17,31,45],"deep":[7],"learning":[8],"(DL),":[9],"has":[10],"achieved":[11],"exceptional":[12],"performances":[13],"many":[15],"tasks":[16],"fields":[18],"such":[19],"as":[20],"natural":[21],"language":[22],"processing":[23],"and":[24,73,101],"computer":[25],"vision.":[26],"For":[27],"certain":[28],"high-stake":[29],"domains,":[30],"addition":[32],"to":[33,49],"desirable":[34],"performance":[35],"metrics,":[36],"a":[37,68,80,97],"high":[38],"level":[39],"of":[40,58],"interpretability":[41],"is":[42],"often":[43],"required":[44],"order":[46],"for":[47,67,93],"AI":[48],"be":[50],"reliably":[51],"utilized.":[52],"Unfortunately,":[53],"the":[54,106,111],"black":[55],"box":[56],"nature":[57],"DL":[59,69],"models":[60],"prevents":[61],"researchers":[62],"from":[63],"providing":[64],"explicative":[65],"descriptions":[66],"model\u2019s":[70,112],"reasoning":[71],"process":[72],"decisions.":[74],"In":[75],"this":[76],"work,":[77],"we":[78],"propose":[79],"novel":[81],"framework":[82],"utilizing":[83],"Adversarial":[84],"Inverse":[85],"Reinforcement":[86,98],"Learning":[87,99],"that":[88,105],"can":[89],"provide":[90],"global":[91],"explanations":[92],"decisions":[94],"made":[95],"by":[96,109],"model":[100,107],"capture":[102],"intuitive":[103],"tendencies":[104],"follows":[108],"summarizing":[110],"decision-making":[113],"process.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}