{"id":"https://openalex.org/W7138245088","doi":"https://doi.org/10.1609/aaai.v40i21.38828","title":"Reducing Goal State Divergence with Environment Design","display_name":"Reducing Goal State Divergence with Environment Design","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138245088","doi":"https://doi.org/10.1609/aaai.v40i21.38828"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i21.38828","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38828","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i21.38828","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129643402","display_name":"Kelsey Sikes","orcid":null},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kelsey Sikes","raw_affiliation_strings":["Colorado State University"],"affiliations":[{"raw_affiliation_string":"Colorado State University","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047553225","display_name":"Sarah Keren","orcid":"https://orcid.org/0000-0001-7211-753X"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sarah Keren","raw_affiliation_strings":["Technion-Israel Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Technion-Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129715583","display_name":"Sarath Sreedharan","orcid":null},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarath Sreedharan","raw_affiliation_strings":["Colorado State University"],"affiliations":[{"raw_affiliation_string":"Colorado State University","institution_ids":["https://openalex.org/I92446798"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5129643402"],"corresponding_institution_ids":["https://openalex.org/I92446798"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56818182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"21","first_page":"17715","last_page":"17723"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.262800008058548,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.262800008058548,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2467000037431717,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.17730000615119934,"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/leverage","display_name":"Leverage (statistics)","score":0.7556999921798706},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.642799973487854},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6039999723434448},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5529000163078308},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5364999771118164},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4478999972343445},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4138000011444092}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7556999921798706},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.642799973487854},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6039999723434448},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5364999771118164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5282999873161316},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37599998712539673},{"id":"https://openalex.org/C84653758","wikidata":"https://www.wikidata.org/wiki/Q5575175","display_name":"Goal orientation","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C42648095","wikidata":"https://www.wikidata.org/wiki/Q7603824","display_name":"State of the Environment","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2736000120639801},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25690001249313354},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i21.38828","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38828","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i21.38828","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38828","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"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":{"Generating":[0],"behaviors":[1],"that":[2,110],"align":[3],"with":[4,24],"human":[5,33,67],"expectations":[6],"is":[7],"a":[8,40,55,61,104],"key":[9],"requirement":[10],"for":[11],"human-robot":[12,96],"collaboration.":[13],"Potential":[14],"behavior":[15],"misalignment":[16],"could":[17],"lead":[18],"to":[19,60],"the":[20,50,53,66,117,124],"robot":[21,56],"performing":[22],"actions":[23],"unanticipated,":[25],"potentially":[26],"dangerous":[27],"side":[28],"effects":[29],"even":[30],"while":[31],"pursuing":[32],"goals.":[34],"In":[35,69],"this":[36],"paper,":[37],"we":[38,77],"introduce":[39],"novel":[41,95],"metric":[42],"called":[43],"Goal":[44],"State":[45],"Divergence":[46],"(GSD)":[47],"which":[48,102],"quantifies":[49],"difference":[51],"between":[52],"state":[54,126],"achieved":[57],"in":[58,93,122],"response":[59],"human-specified":[62],"goal":[63,97,125],"and":[64,86],"what":[65],"expected.":[68],"cases":[70],"where":[71],"GSD":[72,92],"cannot":[73],"be":[74,82],"directly":[75],"calculated,":[76],"show":[78,116],"how":[79],"it":[80],"can":[81,111],"approximated":[83],"using":[84],"maximal":[85],"minimal":[87,105],"bounds.":[88],"We":[89,115],"then":[90],"leverage":[91],"our":[94,120,131],"alignment":[98],"design":[99],"(HRGAD)":[100],"problem,":[101],"identifies":[103],"set":[106],"of":[107,119],"environment":[108],"modifications":[109],"reduce":[112],"such":[113],"mismatches.":[114],"effectiveness":[118],"method":[121],"reducing":[123],"divergence":[127],"by":[128],"empirically":[129],"evaluating":[130],"approach":[132],"on":[133],"several":[134],"planning":[135],"benchmarks.":[136]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}
