{"id":"https://openalex.org/W2912748933","doi":"https://doi.org/10.1007/s10489-019-01417-4","title":"A novel multi-step reinforcement learning method for solving reward hacking","display_name":"A novel multi-step reinforcement learning method for solving reward hacking","publication_year":2019,"publication_date":"2019-02-09","ids":{"openalex":"https://openalex.org/W2912748933","doi":"https://doi.org/10.1007/s10489-019-01417-4","mag":"2912748933"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-019-01417-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-019-01417-4","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","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/A5101184091","display_name":"Yinlong Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinlong Yuan","raw_affiliation_strings":["College of Automation Science and Engineering, South China University of Technology, Guangzhou, 510641, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation Science and Engineering, South China University of Technology, Guangzhou, 510641, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059725501","display_name":"Zhu Liang Yu","orcid":"https://orcid.org/0000-0002-5502-8321"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhu Liang Yu","raw_affiliation_strings":["College of Automation Science and Engineering, South China University of Technology, Guangzhou, 510641, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation Science and Engineering, South China University of Technology, Guangzhou, 510641, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048899636","display_name":"Zhenghui Gu","orcid":"https://orcid.org/0000-0001-9365-2953"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghui Gu","raw_affiliation_strings":["College of Automation Science and Engineering, South China University of Technology, Guangzhou, 510641, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation Science and Engineering, South China University of Technology, Guangzhou, 510641, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100512558","display_name":"Xiaoyan Deng","orcid":"https://orcid.org/0000-0002-5391-766X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Deng","raw_affiliation_strings":["College of Automation Science and Engineering, South China University of Technology, Guangzhou, 510641, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation Science and Engineering, South China University of Technology, Guangzhou, 510641, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100672533","display_name":"Yuanqing Li","orcid":"https://orcid.org/0000-0002-9536-9884"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanqing Li","raw_affiliation_strings":["College of Automation Science and Engineering, South China University of Technology, Guangzhou, 510641, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation Science and Engineering, South China University of Technology, Guangzhou, 510641, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059725501"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.4339,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.70418514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"49","issue":"8","first_page":"2874","last_page":"2888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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":0.9955999851226807,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9555000066757202,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9517999887466431,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8940467238426208},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8681915998458862},{"id":"https://openalex.org/keywords/counterintuitive","display_name":"Counterintuitive","score":0.712841808795929},{"id":"https://openalex.org/keywords/hacker","display_name":"Hacker","score":0.6789126396179199},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49726012349128723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4943113327026367},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4875766634941101},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.48653069138526917},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4210963249206543},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.416686087846756},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4149882197380066},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3808633089065552},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.22797030210494995},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17762801051139832}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8940467238426208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8681915998458862},{"id":"https://openalex.org/C101097943","wikidata":"https://www.wikidata.org/wiki/Q5176983","display_name":"Counterintuitive","level":2,"score":0.712841808795929},{"id":"https://openalex.org/C86844869","wikidata":"https://www.wikidata.org/wiki/Q2798820","display_name":"Hacker","level":2,"score":0.6789126396179199},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49726012349128723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4943113327026367},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4875766634941101},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.48653069138526917},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4210963249206543},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.416686087846756},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4149882197380066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3808633089065552},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.22797030210494995},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17762801051139832},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-019-01417-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-019-01417-4","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4242704309","display_name":"\u57fa\u4e8e\u5728\u7ebf\u5b66\u4e60\u4e0e\u8bc4\u4f30\u7684\u667a\u80fd\u8111\u673a\u5171\u4eab\u63a7\u5236\u6280\u672f\u4e0e\u5eb7\u590d\u5e94\u7528\u7814\u7a76","funder_award_id":"61836003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6980232494","display_name":null,"funder_award_id":"61573150","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":37,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1845972764","https://openalex.org/W1980545744","https://openalex.org/W2066759535","https://openalex.org/W2088222816","https://openalex.org/W2100752967","https://openalex.org/W2113501460","https://openalex.org/W2113921460","https://openalex.org/W2132411323","https://openalex.org/W2145339207","https://openalex.org/W2150339816","https://openalex.org/W2165131254","https://openalex.org/W2172968643","https://openalex.org/W2462906003","https://openalex.org/W2574075983","https://openalex.org/W2593237273","https://openalex.org/W2614309179","https://openalex.org/W2617069179","https://openalex.org/W2621205314","https://openalex.org/W2729602312","https://openalex.org/W2744647809","https://openalex.org/W2745868649","https://openalex.org/W2750866482","https://openalex.org/W2761873684","https://openalex.org/W2768908787","https://openalex.org/W2786928559","https://openalex.org/W2797427442","https://openalex.org/W2805539195","https://openalex.org/W2887039782","https://openalex.org/W2888409681","https://openalex.org/W2897137046","https://openalex.org/W2902293705","https://openalex.org/W2962731213","https://openalex.org/W2963943581","https://openalex.org/W3098163860","https://openalex.org/W3100789280","https://openalex.org/W4298188144"],"related_works":["https://openalex.org/W2809491669","https://openalex.org/W3005839474","https://openalex.org/W2050235149","https://openalex.org/W4379988549","https://openalex.org/W2139510495","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}