{"id":"https://openalex.org/W4285411087","doi":"https://doi.org/10.1109/tai.2022.3190811","title":"A Mutual Information-Based Assessment of Reverse Engineering on Rewards of Reinforcement Learning","display_name":"A Mutual Information-Based Assessment of Reverse Engineering on Rewards of Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-14","ids":{"openalex":"https://openalex.org/W4285411087","doi":"https://doi.org/10.1109/tai.2022.3190811"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2022.3190811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2022.3190811","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Transactions on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.brighton.ac.uk/en/publications/33ae7519-ca2f-427e-a768-eeb8f5e06ce3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042303283","display_name":"Tong Chen","orcid":"https://orcid.org/0000-0003-3851-2135"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Chen","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3851-2135","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070828650","display_name":"Jiqiang Liu","orcid":"https://orcid.org/0000-0003-1147-4327"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqiang Liu","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1147-4327","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065487579","display_name":"Thar Baker","orcid":"https://orcid.org/0000-0002-5166-4873"},"institutions":[{"id":"https://openalex.org/I29891158","display_name":"University of Sharjah","ror":"https://ror.org/00engpz63","country_code":"AE","type":"education","lineage":["https://openalex.org/I29891158"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Thar Baker","raw_affiliation_strings":["Department of Computer Science, College of Computing and Informatics, University of Sharjah, Sharjah, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0002-5166-4873","affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Computing and Informatics, University of Sharjah, Sharjah, United Arab Emirates","institution_ids":["https://openalex.org/I29891158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074589029","display_name":"Yalun Wu","orcid":"https://orcid.org/0000-0002-0891-1904"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yalun Wu","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0891-1904","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049446052","display_name":"Yingxiao Xiang","orcid":"https://orcid.org/0000-0002-8679-7000"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingxiao Xiang","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045240151","display_name":"Yike Li","orcid":"https://orcid.org/0000-0002-6693-0935"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yike Li","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6693-0935","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047248381","display_name":"Wenjia Niu","orcid":"https://orcid.org/0000-0003-4706-4266"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjia Niu","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4706-4266","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085778638","display_name":"Endong Tong","orcid":"https://orcid.org/0000-0003-0348-2108"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Endong Tong","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0348-2108","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015993565","display_name":"Albert Y. Zomaya","orcid":"https://orcid.org/0000-0002-3090-1059"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Albert Y. Zomaya","raw_affiliation_strings":["School of Computer Science, The University of Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3090-1059","affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07492256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":"5","first_page":"1089","last_page":"1100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9517999887466431,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.701789140701294},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.636022686958313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6345422267913818},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5865265130996704},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5849547982215881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5205241441726685},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5091726183891296},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.46675586700439453},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45035088062286377},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23554891347885132},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18656349182128906},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.10973536968231201},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09619283676147461}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.701789140701294},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.636022686958313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6345422267913818},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5865265130996704},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5849547982215881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5205241441726685},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5091726183891296},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46675586700439453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45035088062286377},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23554891347885132},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18656349182128906},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.10973536968231201},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09619283676147461},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tai.2022.3190811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2022.3190811","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Transactions on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/33ae7519-ca2f-427e-a768-eeb8f5e06ce3","is_oa":true,"landing_page_url":"https://research.brighton.ac.uk/en/publications/33ae7519-ca2f-427e-a768-eeb8f5e06ce3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401758","display_name":"University of Brighton Repository (University of Brighton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71637028","host_organization_name":"University of Brighton","host_organization_lineage":["https://openalex.org/I71637028"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chen, T, Liu, J, Baker, T, Wu, Y, Xiang, Y, Li, Y, Niu, W, Tong, E & Zomaya, A 2022, 'A Mutual Information-based Assessment of Reverse Engineering on Rewards of Reinforcement Learning', IEEE Transactions on Artificial Intelligence, pp. 1-13. https://doi.org/10.1109/TAI.2022.3190811","raw_type":"article"},{"id":"pmh:oai:pure.atira.dk:publications/33ae7519-ca2f-427e-a768-eeb8f5e06ce3","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85135237851&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306401758","display_name":"University of Brighton Repository (University of Brighton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71637028","host_organization_name":"University of Brighton","host_organization_lineage":["https://openalex.org/I71637028"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chen, T, Liu, J, Baker, T, Wu, Y, Xiang, Y, Li, Y, Niu, W, Tong, E & Zomaya, A 2022, 'A Mutual Information-based Assessment of Reverse Engineering on Rewards of Reinforcement Learning', IEEE Transactions on Artificial Intelligence, pp. 1-13. https://doi.org/10.1109/TAI.2022.3190811","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/33ae7519-ca2f-427e-a768-eeb8f5e06ce3","is_oa":true,"landing_page_url":"https://research.brighton.ac.uk/en/publications/33ae7519-ca2f-427e-a768-eeb8f5e06ce3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401758","display_name":"University of Brighton Repository (University of Brighton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71637028","host_organization_name":"University of Brighton","host_organization_lineage":["https://openalex.org/I71637028"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chen, T, Liu, J, Baker, T, Wu, Y, Xiang, Y, Li, Y, Niu, W, Tong, E & Zomaya, A 2022, 'A Mutual Information-based Assessment of Reverse Engineering on Rewards of Reinforcement Learning', IEEE Transactions on Artificial Intelligence, pp. 1-13. https://doi.org/10.1109/TAI.2022.3190811","raw_type":"article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G536329181","display_name":null,"funder_award_id":"61966009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5441832261","display_name":null,"funder_award_id":"61802389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5858129093","display_name":"\u667a\u80fd\u4ea4\u901a\u4fe1\u53f7\u706f\u7cfb\u7edf\u4e2d\u6570\u636e\u6295\u6bd2\u653b\u51fb\u7684\u591a\u4e3b\u4f53\u534f\u540c\u9632\u62a4\u7814\u7a76","funder_award_id":"61972025","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6840496190","display_name":null,"funder_award_id":"U1811264","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8091656351","display_name":"\u4e91\u5e73\u53f0\u6570\u636e\u9690\u79c1\u4fdd\u62a4\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61672092","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1559990548","https://openalex.org/W1975463331","https://openalex.org/W1999874108","https://openalex.org/W2021430127","https://openalex.org/W2050612014","https://openalex.org/W2071771048","https://openalex.org/W2098774185","https://openalex.org/W2113023245","https://openalex.org/W2117675763","https://openalex.org/W2162009473","https://openalex.org/W2169498096","https://openalex.org/W2257979135","https://openalex.org/W2287850282","https://openalex.org/W2294521904","https://openalex.org/W2461943168","https://openalex.org/W2583515081","https://openalex.org/W2795859997","https://openalex.org/W2890884856","https://openalex.org/W2898621204","https://openalex.org/W2913191082","https://openalex.org/W2952235417","https://openalex.org/W2963595477","https://openalex.org/W2963844355","https://openalex.org/W2964098908","https://openalex.org/W2964318098","https://openalex.org/W2991138762","https://openalex.org/W3003022110","https://openalex.org/W3048108174","https://openalex.org/W3094572470","https://openalex.org/W3138984732","https://openalex.org/W3159946074","https://openalex.org/W4239584046","https://openalex.org/W4288348902","https://openalex.org/W6633543754","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6677555207","https://openalex.org/W6684097133","https://openalex.org/W6696273291","https://openalex.org/W6697282503","https://openalex.org/W6732948585","https://openalex.org/W6747901993","https://openalex.org/W6754790014","https://openalex.org/W6755489178","https://openalex.org/W6758776091","https://openalex.org/W6762740060","https://openalex.org/W6773721189"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4281847915","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Rewards":[0],"are":[1,104,208],"critical":[2],"hyperparameters":[3],"in":[4,9,65,113,210],"reinforcement":[5,37],"learning":[6,38],"(RL),":[7],"since":[8],"most":[10],"cases":[11],"different":[12,19,244],"reward":[13,61,125],"values":[14,187],"will":[15],"lead":[16],"to":[17,22,48,77,95,136,164],"greatly":[18],"performance.":[20],"Due":[21],"their":[23],"commercial":[24],"value,":[25],"RL":[26],"rewards":[27],"become":[28],"the":[29,35,50,53,59,118,148,153,159,216,230],"target":[30],"of":[31,124,188,219],"reverse":[32],"engineering":[33],"by":[34,141],"inverse":[36],"(IRL)":[39],"algorithm":[40,162],"family.":[41],"Existing":[42],"efforts":[43],"typically":[44],"utilize":[45,158],"two":[46],"metrics":[47,101],"measure":[49],"IRL":[51,132],"performance:":[52],"expected":[54],"value":[55],"difference":[56],"(EVD)":[57],"and":[58,69,102,106,152,191,193,197,200,224,232,241],"mean":[60],"loss":[62],"(MRL).":[63],"Unfortunately,":[64],"some":[66],"cases,":[67],"EVD":[68,85,231,240],"MRL":[70,78,242],"can":[71,183],"give":[72],"completely":[73],"opposite":[74],"results,":[75],"due":[76],"focusing":[79],"on":[80,117,204],"whole":[81],"state-space":[82],"rewards,":[83],"while":[84],"only":[86],"considering":[87,142],"partly":[88],"sampled":[89],"rewards.":[90],"Such":[91],"situation":[92],"naturally":[93],"rises":[94],"one":[96],"fundamental":[97],"question:":[98],"whether":[99],"current":[100],"assessment":[103,199],"sufficient":[105],"accurate":[107,198],"for":[108],"more":[109,195,237],"general":[110],"use.":[111],"Thus,":[112],"this":[114,138],"article,":[115],"based":[116],"metric":[119],"called":[120],"normalized":[121],"mutual":[122],"information":[123],"clusters":[126],"(C-NMI),":[127],"we":[128,134,182],"propose":[129],"a":[130,143,170,180],"novel":[131],"assessment;":[133],"aim":[135],"fill":[137],"research":[139],"gap":[140],"middle-granularity":[144],"state":[145,150],"space":[146,151],"between":[147],"entire":[149],"specific":[154],"sampling":[155],"space.":[156],"We":[157],"agglomerative":[160],"nesting":[161],"(AGNES)":[163],"control":[165],"dynamical":[166],"C-NMI":[167,235],"computing":[168],"via":[169],"fourth-order":[171],"tensor":[172],"model":[173],"with":[174,229],"injected":[175],"manipulated":[176],"trajectories.":[177],"With":[178],"such":[179],"model,":[181],"uniformly":[184],"capture":[185],"different-dimension":[186],"MRL,":[189],"EVD,":[190],"C-NMI,":[192],"perform":[194],"comprehensive":[196],"analyses.":[201],"Extensive":[202],"experiments":[203],"several":[205],"mainstream":[206],"IRLs":[207],"experimented":[209],"object":[211],"world,":[212],"hence":[213],"revealing":[214],"that":[215],"assessing":[217],"accuracy":[218],"our":[220],"method":[221],"increases":[222],"110.13%":[223],"116.59%,":[225],"respectively,":[226],"when":[227],"compared":[228],"MRL.":[233],"Meanwhile,":[234],"is":[236],"robust":[238],"than":[239],"under":[243],"demonstrations.":[245]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}