{"id":"https://openalex.org/W4298112146","doi":"https://doi.org/10.1109/ro-man53752.2022.9900563","title":"Norm Learning with Reward Models from Instructive and Evaluative Feedback","display_name":"Norm Learning with Reward Models from Instructive and Evaluative Feedback","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4298112146","doi":"https://doi.org/10.1109/ro-man53752.2022.9900563"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man53752.2022.9900563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man53752.2022.9900563","pdf_url":null,"source":{"id":"https://openalex.org/S4363607995","display_name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5046853629","display_name":"Eric Rosen","orcid":"https://orcid.org/0000-0002-0223-4324"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Rosen","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028560428","display_name":"Eric Hsiung","orcid":null},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Hsiung","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064997007","display_name":"Vivienne Bihe","orcid":"https://orcid.org/0000-0002-2425-0317"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivienne Bihe Chi","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090962780","display_name":"Bertram F. Malle","orcid":"https://orcid.org/0000-0003-0845-9601"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bertram F. Malle","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I175594653"],"apc_list":null,"apc_paid":null,"fwci":0.8304,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7451895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1634","last_page":"1640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9771999716758728,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9593999981880188,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5546832084655762},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.5444463491439819},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.419366717338562},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4140802323818207},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.352469265460968},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33148062229156494},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.32233452796936035},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.13991612195968628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5546832084655762},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.5444463491439819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.419366717338562},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4140802323818207},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.352469265460968},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33148062229156494},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.32233452796936035},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.13991612195968628},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man53752.2022.9900563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man53752.2022.9900563","pdf_url":null,"source":{"id":"https://openalex.org/S4363607995","display_name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W141430544","https://openalex.org/W1985795534","https://openalex.org/W1989596494","https://openalex.org/W1999874108","https://openalex.org/W2104802329","https://openalex.org/W2114864106","https://openalex.org/W2121110499","https://openalex.org/W2343904395","https://openalex.org/W2569421824","https://openalex.org/W2900406861","https://openalex.org/W2910773760","https://openalex.org/W2945642643","https://openalex.org/W2952209611","https://openalex.org/W2966120739","https://openalex.org/W3000002597","https://openalex.org/W3006303816","https://openalex.org/W3037533353","https://openalex.org/W3046965165","https://openalex.org/W3187304456","https://openalex.org/W3191508855","https://openalex.org/W3197594072","https://openalex.org/W4232528696","https://openalex.org/W4249362117","https://openalex.org/W4300110528","https://openalex.org/W4312740067","https://openalex.org/W4313005643","https://openalex.org/W6677151524","https://openalex.org/W6732417791","https://openalex.org/W6774122581"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"People":[0],"are":[1,178],"increasingly":[2],"interacting":[3],"with":[4],"artificial":[5],"agents":[6,13],"in":[7,150],"social":[8,23],"settings,":[9],"and":[10,36,61,75,93,130,146,164],"as":[11,67,89],"these":[12],"become":[14],"more":[15],"sophisticated,":[16],"people":[17,49],"will":[18],"have":[19],"to":[20,34,57,116,136,142,169,180,189],"teach":[21],"them":[22],"norms.":[24,121],"Two":[25],"prominent":[26],"teaching":[27,55,99,138],"methods":[28,53,65,100,139],"include":[29],"instructing":[30],"the":[31,41,64,71,97,118,160],"learner":[32],"how":[33],"act,":[35],"giving":[37],"evaluative":[38],"feedback":[39,171],"on":[40],"learner\u2019s":[42],"actions.":[43],"Our":[44],"empirical":[45],"findings":[46],"indicate":[47],"that":[48,111,132],"naturally":[50],"adopt":[51],"both":[52,137],"when":[54],"norms":[56,88],"a":[58,68,84,90,102,108,133,151,155,185],"simulated":[59],"robot,":[60],"they":[62],"use":[63],"selectively":[66],"function":[69,92,110],"of":[70,86],"robot\u2019s":[72,161],"perceived":[73],"expertise":[74],"learning":[76,95,125,162],"progress.":[77],"In":[78],"our":[79],"algorithmic":[80],"work,":[81],"we":[82],"conceptualize":[83],"set":[85],"context-specific":[87],"reward":[91,109],"integrate":[94],"from":[96],"two":[98],"under":[101,126],"single":[103],"likelihood-based":[104],"algorithm,":[105],"which":[106],"estimates":[107],"induces":[112],"policies":[113],"maximally":[114],"likely":[115],"satisfy":[117],"teacher\u2019s":[119],"intended":[120],"We":[122,158],"compare":[123],"robot":[124,134],"various":[127],"teacher":[128],"models":[129],"demonstrate":[131],"responsive":[135],"can":[140],"learn":[141],"reach":[143],"its":[144],"goal":[145],"minimize":[147],"norm":[148],"violations":[149],"navigation":[152],"task":[153],"for":[154],"grid":[156],"world.":[157],"improve":[159],"speed":[163],"performance":[165],"by":[166],"enabling":[167],"teachers":[168],"give":[170],"at":[172,184],"an":[173],"abstract":[174],"level":[175,187],"(which":[176],"rooms":[177],"acceptable":[179],"navigate)":[181],"rather":[182],"than":[183],"low":[186],"(how":[188],"navigate":[190],"any":[191],"particular":[192],"room).":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}