{"id":"https://openalex.org/W4406316598","doi":"https://doi.org/10.1109/icmla66185.2025.00158","title":"Strategy Masking: A Method for Guardrails in Value-based Reinforcement Learning Agents","display_name":"Strategy Masking: A Method for Guardrails in Value-based Reinforcement Learning Agents","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4406316598","doi":"https://doi.org/10.1109/icmla66185.2025.00158"},"language":"en","primary_location":{"id":"doi:10.1109/icmla66185.2025.00158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.05501","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017778869","display_name":"Jonathan Keane","orcid":null},"institutions":[{"id":"https://openalex.org/I50702494","display_name":"Milwaukee School of Engineering","ror":"https://ror.org/04h7cfr36","country_code":"US","type":"education","lineage":["https://openalex.org/I50702494"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jonathan Keane","raw_affiliation_strings":["Milwaukee School of Engineering,Diercks School of Advanced Computing,Milwaukee,WI,USA"],"affiliations":[{"raw_affiliation_string":"Milwaukee School of Engineering,Diercks School of Advanced Computing,Milwaukee,WI,USA","institution_ids":["https://openalex.org/I50702494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066328030","display_name":"Sam Keyser","orcid":null},"institutions":[{"id":"https://openalex.org/I50702494","display_name":"Milwaukee School of Engineering","ror":"https://ror.org/04h7cfr36","country_code":"US","type":"education","lineage":["https://openalex.org/I50702494"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Keyser","raw_affiliation_strings":["Milwaukee School of Engineering,Diercks School of Advanced Computing,Milwaukee,WI,USA"],"affiliations":[{"raw_affiliation_string":"Milwaukee School of Engineering,Diercks School of Advanced Computing,Milwaukee,WI,USA","institution_ids":["https://openalex.org/I50702494"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100030177","display_name":"Jeremy Kedziora","orcid":null},"institutions":[{"id":"https://openalex.org/I50702494","display_name":"Milwaukee School of Engineering","ror":"https://ror.org/04h7cfr36","country_code":"US","type":"education","lineage":["https://openalex.org/I50702494"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Kedziora","raw_affiliation_strings":["Milwaukee School of Engineering,Diercks School of Advanced Computing,Milwaukee,WI,USA"],"affiliations":[{"raw_affiliation_string":"Milwaukee School of Engineering,Diercks School of Advanced Computing,Milwaukee,WI,USA","institution_ids":["https://openalex.org/I50702494"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017778869"],"corresponding_institution_ids":["https://openalex.org/I50702494"],"apc_list":null,"apc_paid":null,"fwci":1.1537,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73595107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1040","last_page":"1045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.19359999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.19359999895095825,"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"}},{"id":"https://openalex.org/T14351","display_name":"Statistical and Computational Modeling","score":0.19130000472068787,"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/T11182","display_name":"Auction Theory and Applications","score":0.16590000689029694,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.7423720955848694},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7049186825752258},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6661797761917114},{"id":"https://openalex.org/keywords/masking-agent","display_name":"Masking agent","score":0.48243412375450134},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.47758248448371887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3860134482383728},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3217313289642334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3132004737854004},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1902158558368683},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1395741105079651},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.12281548976898193},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.03977996110916138},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.03472521901130676},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.03420153260231018}],"concepts":[{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7423720955848694},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7049186825752258},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6661797761917114},{"id":"https://openalex.org/C14538495","wikidata":"https://www.wikidata.org/wiki/Q641765","display_name":"Masking agent","level":2,"score":0.48243412375450134},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.47758248448371887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3860134482383728},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3217313289642334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3132004737854004},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1902158558368683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1395741105079651},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.12281548976898193},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.03977996110916138},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.03472521901130676},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.03420153260231018}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icmla66185.2025.00158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.05501","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.05501","pdf_url":"https://arxiv.org/pdf/2501.05501","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.05501","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.05501","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.05501","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.05501","pdf_url":"https://arxiv.org/pdf/2501.05501","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4406316598.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2380924560","https://openalex.org/W2014113800","https://openalex.org/W2038223616","https://openalex.org/W1969211203","https://openalex.org/W2364208171","https://openalex.org/W3138029823","https://openalex.org/W1985388337","https://openalex.org/W1880394600","https://openalex.org/W2332718375","https://openalex.org/W2481555009"],"abstract_inverted_index":{"The":[0],"use":[1,58],"of":[2,24],"reward":[3,28,59],"functions":[4,60],"to":[5,14,35,61,75,89,102,115],"structure":[6],"AI":[7,55,82,93],"learning":[8,18],"and":[9,78,95],"decision":[10,63],"making":[11],"is":[12],"core":[13],"the":[15,25],"current":[16],"reinforcement":[17],"paradigm;":[19],"however,":[20],"without":[21,111],"thorough":[22],"understanding":[23],"incentives":[26],"a":[27,67],"function":[29],"creates,":[30],"it":[31,98],"can":[32,99],"be":[33,100],"difficult":[34],"impose":[36],"principled":[37],"yet":[38],"general":[39],"control":[40],"mechanisms":[41],"over":[42],"its":[43],"behavior.":[44,84],"In":[45],"this":[46],"paper,":[47],"we":[48,71],"study":[49,90],"methods":[50],"for":[51,54],"constructing":[52],"guardrails":[53],"agents":[56,94],"that":[57,97],"learn":[62,77],"making.":[64],"We":[65,85],"introduce":[66],"novel":[68],"approach,":[69],"which":[70],"call":[72],"strategy":[73],"masking,":[74],"explicitly":[76],"then":[79],"suppress":[80],"undesirable":[81],"agent":[83,105,113],"apply":[86],"our":[87],"method":[88],"lying":[91,109],"in":[92],"show":[96],"used":[101],"effectively":[103],"modify":[104],"behavior":[106],"by":[107],"suppressing":[108],"post-training":[110],"compromising":[112],"ability":[114],"perform":[116],"effectively.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2025-10-10T00:00:00"}