{"id":"https://openalex.org/W4415428517","doi":"https://doi.org/10.3233/faia251093","title":"An Approximate Embedding for Designing Ethical Reinforcement Learning Environments","display_name":"An Approximate Embedding for Designing Ethical Reinforcement Learning Environments","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428517","doi":"https://doi.org/10.3233/faia251093"},"language":null,"primary_location":{"id":"doi:10.3233/faia251093","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251093","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251093","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119705133","display_name":"Arnau Mayoral-Macau","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Arnau Mayoral-Macau","raw_affiliation_strings":["IIIA-CSIC, Spain"],"affiliations":[{"raw_affiliation_string":"IIIA-CSIC, Spain","institution_ids":["https://openalex.org/I4210131846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080841253","display_name":"Manel Rodr\u00edguez-Soto","orcid":"https://orcid.org/0000-0003-1339-2018"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Manel Rodriguez-Soto","raw_affiliation_strings":["IIIA-CSIC, Spain"],"affiliations":[{"raw_affiliation_string":"IIIA-CSIC, Spain","institution_ids":["https://openalex.org/I4210131846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058298540","display_name":"Enrico Marchesini","orcid":"https://orcid.org/0000-0003-1858-7279"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Enrico Marchesini","raw_affiliation_strings":["Massachusetts Institute of Technology, Boston, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Boston, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067606642","display_name":"Mart\u00ed S\u00e1nchez-Fibla","orcid":"https://orcid.org/0000-0001-5725-1984"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mart\u00ed S\u00e1nchez-Fibla","raw_affiliation_strings":["IIIA-CSIC, Spain"],"affiliations":[{"raw_affiliation_string":"IIIA-CSIC, Spain","institution_ids":["https://openalex.org/I4210131846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028762293","display_name":"Maite L\u00f3pez-S\u00e1nchez","orcid":"https://orcid.org/0000-0002-1838-5928"},"institutions":[{"id":"https://openalex.org/I71999127","display_name":"Universitat de Barcelona","ror":"https://ror.org/021018s57","country_code":"ES","type":"education","lineage":["https://openalex.org/I71999127"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Maite L\u00f3pez-S\u00e1nchez","raw_affiliation_strings":["Universitat de Barcelona"],"affiliations":[{"raw_affiliation_string":"Universitat de Barcelona","institution_ids":["https://openalex.org/I71999127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005383856","display_name":"Juan A. Rodr\u00edguez-Aguilar","orcid":"https://orcid.org/0000-0002-2940-6886"},"institutions":[{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan Antonio Rodr\u00edguez-Aguilar","raw_affiliation_strings":["IIIA-CSIC, Spain"],"affiliations":[{"raw_affiliation_string":"IIIA-CSIC, Spain","institution_ids":["https://openalex.org/I4210131846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045922629","display_name":"Alessandro Farinelli","orcid":"https://orcid.org/0000-0002-2592-5814"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Farinelli","raw_affiliation_strings":["Department of Computer Science, University of Verona, Verona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5119705133"],"corresponding_institution_ids":["https://openalex.org/I4210131846"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50706584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8149999976158142,"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":0.8149999976158142,"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/T11883","display_name":"Embodied and Extended Cognition","score":0.7504000067710876,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.774399995803833},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.593999981880188},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5723000168800354},{"id":"https://openalex.org/keywords/beneficence","display_name":"Beneficence","score":0.5285000205039978},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.453000009059906},{"id":"https://openalex.org/keywords/ethical-issues","display_name":"Ethical issues","score":0.33739998936653137}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.774399995803833},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.593999981880188},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5723000168800354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5507000088691711},{"id":"https://openalex.org/C117438556","wikidata":"https://www.wikidata.org/wiki/Q4887413","display_name":"Beneficence","level":3,"score":0.5285000205039978},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4260999858379364},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3682999908924103},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.34610000252723694},{"id":"https://openalex.org/C2986663376","wikidata":"https://www.wikidata.org/wiki/Q9465","display_name":"Ethical issues","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3240000009536743},{"id":"https://openalex.org/C34972735","wikidata":"https://www.wikidata.org/wiki/Q2920267","display_name":"Engineering design process","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C48262172","wikidata":"https://www.wikidata.org/wiki/Q16908765","display_name":"Design process","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C2778365744","wikidata":"https://www.wikidata.org/wiki/Q2426689","display_name":"Learning environment","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.2685999870300293}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251093","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251093","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251093","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251093","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"the":[3,12,59,79,83,98],"Approximate":[4],"Ethical":[5],"Embedding":[6],"Process,":[7],"an":[8,33,68],"algorithm":[9,21],"for":[10,17,53,63],"automating":[11],"design":[13,61],"of":[14,67,82,100],"ethical":[15,34,55,60],"environments":[16,24,95],"learning":[18,99],"agents.":[19],"Our":[20,85],"helps":[22],"build":[23],"wherein":[25],"multiple":[26],"agents":[27,71],"learn":[28],"policies":[29],"that":[30,88,96],"align":[31],"with":[32,50],"(moral)":[35],"value":[36],"while":[37],"simultaneously":[38],"pursuing":[39],"their":[40],"individual":[41],"objectives.":[42],"Therefore,":[43],"we":[44],"contribute":[45],"to":[46,73,75,77],"endowing":[47],"environment":[48,69],"designers":[49],"algorithmic":[51],"tools":[52],"building":[54],"environments.":[56],"We":[57],"demonstrate":[58],"process":[62,92],"two":[64],"different":[65],"settings":[66],"where":[70],"have":[72],"adhere":[74],"beneficence":[76],"promote":[78],"collective":[80],"survival":[81],"population.":[84],"experiments":[86],"show":[87],"our":[89],"approximate":[90],"embedding":[91],"successfully":[93],"generates":[94],"incentivise":[97],"value-aligned":[101],"policies.":[102]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}