{"id":"https://openalex.org/W3191508855","doi":"https://doi.org/10.1145/3461702.3462473","title":"Training for Implicit Norms in Deep Reinforcement Learning Agents through Adversarial Multi-Objective Reward Optimization","display_name":"Training for Implicit Norms in Deep Reinforcement Learning Agents through Adversarial Multi-Objective Reward Optimization","publication_year":2021,"publication_date":"2021-07-21","ids":{"openalex":"https://openalex.org/W3191508855","doi":"https://doi.org/10.1145/3461702.3462473","mag":"3191508855"},"language":"en","primary_location":{"id":"doi:10.1145/3461702.3462473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461702.3462473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-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/A5041915956","display_name":"Markus F. Peschl","orcid":"https://orcid.org/0000-0002-0876-6663"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Markus Peschl","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041915956"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6280826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976000189781189,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976000189781189,"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":0.9962999820709229,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9508000016212463,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9073190689086914},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8278947472572327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.726334810256958},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6933823227882385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6399452686309814},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4920615553855896},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4487369656562805},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42758041620254517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11709922552108765}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9073190689086914},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8278947472572327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.726334810256958},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6933823227882385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6399452686309814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4920615553855896},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4487369656562805},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42758041620254517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11709922552108765},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3461702.3462473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461702.3462473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:af9eea33-1fa7-4cdd-8278-d7a0da05736e","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:af9eea33-1fa7-4cdd-8278-d7a0da05736e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2772337934","https://openalex.org/W2886362482","https://openalex.org/W2973186106","https://openalex.org/W3135252453"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"We":[0,73],"propose":[1],"a":[2,22,78],"deep":[3],"reinforcement":[4,33],"learning":[5,34],"algorithm":[6,45],"that":[7],"employs":[8],"an":[9],"adversarial":[10],"training":[11],"strategy":[12],"for":[13,21,61],"adhering":[14],"to":[15,52,97],"implicit":[16],"human":[17,30,57,88],"norms":[18,55],"alongside":[19],"optimizing":[20],"narrow":[23],"goal":[24],"objective.":[25],"Previous":[26],"methods":[27],"which":[28,59],"incorporate":[29],"values":[31],"into":[32,64],"algorithms":[35],"either":[36],"scale":[37],"poorly":[38],"or":[39],"assume":[40],"hand-crafted":[41],"state":[42],"features.":[43],"Our":[44],"drops":[46],"these":[47],"assumptions":[48],"and":[49,82],"is":[50],"able":[51],"automatically":[53],"infer":[54],"from":[56],"demonstrations,":[58],"allows":[60],"integrating":[62],"it":[63],"existing":[65],"agents":[66],"in":[67,77],"the":[68,98],"form":[69],"of":[70],"multi-objective":[71],"optimization.":[72],"benchmark":[74],"our":[75,90],"approach":[76],"search-and-rescue":[79],"grid":[80],"world":[81],"show":[83],"that,":[84],"conditioned":[85],"on":[86],"respecting":[87],"norms,":[89],"agent":[91],"maintains":[92],"optimal":[93],"performance":[94],"with":[95],"respect":[96],"predefined":[99],"goal.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}