{"id":"https://openalex.org/W4386242333","doi":"https://doi.org/10.1145/3600211.3604698","title":"Reward Reports for Reinforcement Learning","display_name":"Reward Reports for Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-08","ids":{"openalex":"https://openalex.org/W4386242333","doi":"https://doi.org/10.1145/3600211.3604698"},"language":"en","primary_location":{"id":"doi:10.1145/3600211.3604698","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3600211.3604698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 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/A5103141675","display_name":"Thomas Krendl Gilbert","orcid":"https://orcid.org/0000-0003-1029-4535"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thomas Krendl Gilbert","raw_affiliation_strings":["Cornell Tech, USA"],"affiliations":[{"raw_affiliation_string":"Cornell Tech, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083548887","display_name":"Nathan Lambert","orcid":"https://orcid.org/0000-0002-9997-6817"},"institutions":[{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":null,"type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Lambert","raw_affiliation_strings":["Hugging Face, USA"],"affiliations":[{"raw_affiliation_string":"Hugging Face, USA","institution_ids":["https://openalex.org/I4387154989"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029554720","display_name":"Sarah Dean","orcid":"https://orcid.org/0000-0002-5614-3532"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Dean","raw_affiliation_strings":["Cornell University, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072598105","display_name":"Tom Zick","orcid":"https://orcid.org/0009-0005-4148-2004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Zick","raw_affiliation_strings":["Harvard Law School, USA"],"affiliations":[{"raw_affiliation_string":"Harvard Law School, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091885274","display_name":"Aaron Snoswell","orcid":"https://orcid.org/0000-0003-0960-0144"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Aaron Snoswell","raw_affiliation_strings":["University of Queensland, Australia"],"affiliations":[{"raw_affiliation_string":"University of Queensland, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103202203","display_name":"S Mehta","orcid":"https://orcid.org/0009-0003-0685-5923"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soham Mehta","raw_affiliation_strings":["Columbia University, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103141675"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":5.6674,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.96624943,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9873999953269958,"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"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9873999953269958,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9861999750137329,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8304266929626465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7941837906837463},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6135759949684143},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.5853819251060486},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.5265246629714966},{"id":"https://openalex.org/keywords/chatbot","display_name":"Chatbot","score":0.5164973139762878},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4405423700809479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41752058267593384},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35404151678085327},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.24570736289024353}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8304266929626465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7941837906837463},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6135759949684143},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.5853819251060486},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.5265246629714966},{"id":"https://openalex.org/C2779041454","wikidata":"https://www.wikidata.org/wiki/Q870780","display_name":"Chatbot","level":2,"score":0.5164973139762878},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4405423700809479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41752058267593384},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35404151678085327},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.24570736289024353},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3600211.3604698","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3600211.3604698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327705","display_name":"Mozilla Foundation","ror":"https://ror.org/01y8r3379"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2768432182","https://openalex.org/W2788007910","https://openalex.org/W2897042519","https://openalex.org/W2897154134","https://openalex.org/W2898027304","https://openalex.org/W2904466241","https://openalex.org/W2921848501","https://openalex.org/W2974071289","https://openalex.org/W2989512989","https://openalex.org/W3001807593","https://openalex.org/W3017205423","https://openalex.org/W3034344071","https://openalex.org/W3095615755","https://openalex.org/W3100279624","https://openalex.org/W3108071511","https://openalex.org/W3112486745","https://openalex.org/W3118210634","https://openalex.org/W3128621548","https://openalex.org/W3135252453","https://openalex.org/W3135371071","https://openalex.org/W3154536706","https://openalex.org/W3156242690","https://openalex.org/W3175934762","https://openalex.org/W3193464862","https://openalex.org/W3199782056","https://openalex.org/W3204130547","https://openalex.org/W3212368439","https://openalex.org/W3212932045","https://openalex.org/W4214562898","https://openalex.org/W4246270964","https://openalex.org/W4283157845","https://openalex.org/W4288083797","https://openalex.org/W4312236423"],"related_works":["https://openalex.org/W4383501580","https://openalex.org/W4214931137","https://openalex.org/W4387007686","https://openalex.org/W4313813117","https://openalex.org/W4382052417","https://openalex.org/W3192088754","https://openalex.org/W3084631705","https://openalex.org/W3176146353","https://openalex.org/W4293646425","https://openalex.org/W4379781060"],"abstract_inverted_index":{"Building":[0],"systems":[1],"that":[2,65,116],"are":[3,134,184],"good":[4],"for":[5,32,88,172],"society":[6],"in":[7,43,60,106,186],"the":[8,27,49,66,155,187],"face":[9],"of":[10,29,51,68,149,157],"complex":[11],"societal":[12],"effects":[13,67],"requires":[14],"a":[15,44,86,126,158,163],"dynamic":[16,138],"approach.":[17],"Recent":[18],"approaches":[19],"to":[20,119,136],"machine":[21],"learning":[22,62,94],"(ML)":[23],"documentation":[24],"have":[25,40],"demonstrated":[26],"promise":[28],"discursive":[30],"frameworks":[31],"deliberation":[33],"about":[34],"these":[35,38],"complexities.":[36],"However,":[37],"developments":[39],"been":[41],"grounded":[42],"static":[45,147],"ML":[46],"paradigm,":[47],"leaving":[48],"role":[50],"feedback":[52,69],"and":[53,70,79,91,122,179],"post-deployment":[54],"performance":[55],"unexamined.":[56],"Meanwhile,":[57],"recent":[58],"work":[59],"reinforcement":[61,107],"has":[63],"shown":[64],"optimization":[71],"objectives":[72],"on":[73],"system":[74,129,142],"behavior":[75],"can":[76],"be":[77],"wide-ranging":[78],"unpredictable.":[80],"In":[81],"this":[82],"paper":[83],"we":[84,97,109,161],"sketch":[85],"framework":[87],"documenting":[89],"deployed":[90],"iteratively":[92],"updated":[93],"systems,":[95],"which":[96],"call":[98],"Reward":[99,111,159],"Reports.":[100],"Taking":[101],"inspiration":[102],"from":[103,141],"technical":[104],"concepts":[105],"learning,":[108],"outline":[110],"Reports":[112],"as":[113],"living":[114],"documents":[115],"track":[117,137],"updates":[118],"design":[120],"choices":[121],"assumptions":[123],"behind":[124],"what":[125],"particular":[127],"automated":[128],"is":[130],"optimizing":[131],"for.":[132],"They":[133],"intended":[135],"phenomena":[139],"arising":[140],"deployment,":[143],"rather":[144],"than":[145],"merely":[146],"properties":[148],"models":[150],"or":[151],"data.":[152],"After":[153],"presenting":[154],"elements":[156],"Report,":[160],"discuss":[162],"concrete":[164],"example:":[165],"Meta\u2019s":[166],"BlenderBot":[167],"3":[168],"chatbot.":[169],"Several":[170],"others":[171],"game-playing":[173],"(DeepMind\u2019s":[174],"MuZero),":[175],"content":[176],"recommendation":[177],"(MovieLens),":[178],"traffic":[180],"control":[181],"(Project":[182],"Flow)":[183],"included":[185],"appendix.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
