{"id":"https://openalex.org/W3087775435","doi":"https://doi.org/10.1007/978-981-15-9031-3_11","title":"A Configurable off-Policy Evaluation with Key State-Based Bias Constraints in AI Reinforcement Learning","display_name":"A Configurable off-Policy Evaluation with Key State-Based Bias Constraints in AI Reinforcement Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3087775435","doi":"https://doi.org/10.1007/978-981-15-9031-3_11","mag":"3087775435"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-15-9031-3_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-15-9031-3_11","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},"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/A5040209326","display_name":"Shuo-Ru Wang","orcid":null},"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":"Shuoru Wang","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Haidian District, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Haidian District, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108529463","display_name":"Jiqiang Liu","orcid":null},"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, Haidian District, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Haidian District, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461286","display_name":"Tong Chen","orcid":"https://orcid.org/0000-0003-2751-2412"},"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, Haidian District, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Haidian District, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100661186","display_name":"Li He","orcid":"https://orcid.org/0000-0002-0685-3309"},"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":"He Li","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Haidian District, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Haidian District, 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, Haidian District, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Haidian District, 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, Haidian District, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Haidian District, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408780","display_name":"Long Li","orcid":"https://orcid.org/0000-0002-7693-9722"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Li","raw_affiliation_strings":["Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102373016","display_name":"Minglu Song","orcid":null},"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":"Minglu Song","raw_affiliation_strings":["Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Haidian District, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Haidian District, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10804","display_name":"Health Systems, Economic Evaluations, Quality of Life","score":0.9769999980926514,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9153000116348267,"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/computer-science","display_name":"Computer science","score":0.7183356881141663},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6913530826568604},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6309547424316406},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6203449368476868},{"id":"https://openalex.org/keywords/expected-return","display_name":"Expected return","score":0.4514238238334656},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.45056596398353577},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43162068724632263},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4276789128780365},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4106253981590271},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3711813688278198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3681989312171936},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13357263803482056},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13202187418937683},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.10645166039466858},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10099583864212036},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09825906157493591}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183356881141663},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6913530826568604},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6309547424316406},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6203449368476868},{"id":"https://openalex.org/C154611145","wikidata":"https://www.wikidata.org/wiki/Q4331879","display_name":"Expected return","level":3,"score":0.4514238238334656},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.45056596398353577},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43162068724632263},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4276789128780365},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4106253981590271},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3711813688278198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3681989312171936},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13357263803482056},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13202187418937683},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.10645166039466858},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10099583864212036},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09825906157493591},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-15-9031-3_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-15-9031-3_11","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1095970959","https://openalex.org/W1514587017","https://openalex.org/W1585861384","https://openalex.org/W1971712327","https://openalex.org/W2008949192","https://openalex.org/W2064853889","https://openalex.org/W2108692343","https://openalex.org/W2119567691","https://openalex.org/W2150291618","https://openalex.org/W2273088453","https://openalex.org/W2275802500","https://openalex.org/W2340679559","https://openalex.org/W2425855276","https://openalex.org/W2953633867","https://openalex.org/W2962785510","https://openalex.org/W2964055673","https://openalex.org/W4298023569","https://openalex.org/W6738317309"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
