{"id":"https://openalex.org/W4313529721","doi":"https://doi.org/10.1145/3568162.3576989","title":"SIRL","display_name":"SIRL","publication_year":2023,"publication_date":"2023-03-09","ids":{"openalex":"https://openalex.org/W4313529721","doi":"https://doi.org/10.1145/3568162.3576989"},"language":"en","primary_location":{"id":"doi:10.1145/3568162.3576989","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3568162.3576989","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3568162.3576989","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3568162.3576989","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034978137","display_name":"Andreea Bobu","orcid":"https://orcid.org/0000-0002-9507-7427"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andreea Bobu","raw_affiliation_strings":["University of California Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330490","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0002-1105-0033"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["University of California Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012971694","display_name":"Rohin Shah","orcid":"https://orcid.org/0000-0002-0656-2800"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rohin Shah","raw_affiliation_strings":["DeepMind Research, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind Research, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103065575","display_name":"Daniel S. Brown","orcid":"https://orcid.org/0000-0002-9570-1832"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel S. Brown","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005997281","display_name":"Anca D. Dragan","orcid":"https://orcid.org/0000-0001-6312-5466"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anca D. Dragan","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5034978137"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":9.4305,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97394368,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"565","last_page":"574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12890","display_name":"Eurasian Exchange Networks","score":0.871999979019165,"subfield":{"id":"https://openalex.org/subfields/3314","display_name":"Anthropology"},"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/T12890","display_name":"Eurasian Exchange Networks","score":0.871999979019165,"subfield":{"id":"https://openalex.org/subfields/3314","display_name":"Anthropology"},"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/T12745","display_name":"Dietary Effects on Health","score":0.86080002784729,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5713992714881897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5713992714881897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3568162.3576989","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3568162.3576989","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3568162.3576989","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2301.00810","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.00810","pdf_url":"https://arxiv.org/pdf/2301.00810","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3568162.3576989","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3568162.3576989","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3568162.3576989","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G6894402473","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313529721.pdf","grobid_xml":"https://content.openalex.org/works/W4313529721.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W85455704","https://openalex.org/W180242331","https://openalex.org/W343636949","https://openalex.org/W1252856208","https://openalex.org/W1551864151","https://openalex.org/W1567876833","https://openalex.org/W1583837637","https://openalex.org/W1754243990","https://openalex.org/W1830239953","https://openalex.org/W1987768879","https://openalex.org/W1999874108","https://openalex.org/W2058199791","https://openalex.org/W2067906953","https://openalex.org/W2078158966","https://openalex.org/W2119914747","https://openalex.org/W2158582431","https://openalex.org/W2181849516","https://openalex.org/W2604763608","https://openalex.org/W2609547559","https://openalex.org/W2612112834","https://openalex.org/W2735318784","https://openalex.org/W2753738274","https://openalex.org/W2763110165","https://openalex.org/W2769520592","https://openalex.org/W2785324569","https://openalex.org/W2802553787","https://openalex.org/W2890721972","https://openalex.org/W2912269676","https://openalex.org/W2930682606","https://openalex.org/W2962937519","https://openalex.org/W2963226019","https://openalex.org/W2963391602","https://openalex.org/W2964021598","https://openalex.org/W2964127395","https://openalex.org/W2970370999","https://openalex.org/W2971218263","https://openalex.org/W2973082937","https://openalex.org/W3000384245","https://openalex.org/W3005680577","https://openalex.org/W3006303816","https://openalex.org/W3006334608","https://openalex.org/W3008082783","https://openalex.org/W3022566517","https://openalex.org/W3091362478","https://openalex.org/W3101780148","https://openalex.org/W3115293622","https://openalex.org/W3136987292","https://openalex.org/W3139794247","https://openalex.org/W3149322120","https://openalex.org/W3175995235","https://openalex.org/W3206918183","https://openalex.org/W3213695441","https://openalex.org/W4225737910","https://openalex.org/W4226182032","https://openalex.org/W4281682128","https://openalex.org/W4288076204","https://openalex.org/W4289419964","https://openalex.org/W4294201702","https://openalex.org/W4295095148","https://openalex.org/W4300116964","https://openalex.org/W4300198501","https://openalex.org/W4321392130","https://openalex.org/W4391602018","https://openalex.org/W6636447180"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"When":[0],"robots":[1,93],"learn":[2,20,243,252],"reward":[3,61],"functions":[4],"using":[5],"high":[6],"capacity":[7],"models":[8],"that":[9,72,101,117,139,160,218,246,274],"take":[10],"raw":[11],"state":[12],"directly":[13],"as":[14,34,36,185,187,265,267],"input,":[15],"they":[16,47,109,129],"need":[17],"to":[18,38,49,57,66,81,83,91,94,171,176,224,242,281],"both":[19,51],"a":[21,43,70,207,213,232,269],"representation":[22,71,123,180,215],"for":[23],"what":[24,127,167,174,182,188],"matters":[25],"in":[26,76,164,210,240,268],"the":[27,30,59,77,98,137,158,169,179,244],"task":[28,31],"---":[29,33],"\"features\"":[32],"well":[35,186,266],"how":[37],"combine":[39],"these":[40],"features":[41,100,138,159],"into":[42,121,178],"single":[44],"objective.":[45],"If":[46],"try":[48],"do":[50],"at":[52],"once":[53],"from":[54,286],"input":[55],"designed":[56],"teach":[58],"full":[60],"function,":[62],"it":[63],"is":[64,90,116,147,166,183,229],"easy":[65],"end":[67],"up":[68],"with":[69],"contains":[73],"spurious":[74],"correlations":[75],"data,":[78],"which":[79],"fails":[80],"generalize":[82],"new":[84],"settings.":[85],"Instead,":[86],"our":[87],"ultimate":[88],"goal":[89],"enable":[92],"identify":[95],"and":[96,106,112,255,294],"isolate":[97],"causal":[99],"people":[102,247],"actually":[103],"care":[104],"about":[105],"use":[107,258],"when":[108],"represent":[110],"states":[111],"behavior.":[113],"Our":[114],"idea":[115],"we":[118,250,257,272],"can":[119,192,251],"tune":[120],"this":[122],"by":[124,231],"asking":[125],"users":[126],"behaviors":[128,132,150],"consider":[130],"similar:":[131],"will":[133,151],"be":[134,152,193],"similar":[135,221,225],"if":[136,144,154],"matter":[140,161],"are":[141,288],"similar,":[142],"even":[143,155],"low-level":[145],"behavior":[146,191],"different;":[148],"conversely,":[149],"different":[153],"one":[156],"of":[157,190,200,261],"differs.":[162],"This,":[163],"turn,":[165],"enables":[168],"robot":[170],"disambiguate":[172],"between":[173],"needs":[175],"go":[177],"versus":[181,196],"spurious,":[184],"aspects":[189],"compressed":[194],"together":[195],"not.":[197],"The":[198],"notion":[199],"learning":[201,216,275],"representations":[202,245,282],"based":[203],"on":[204],"similarity":[205,228,278],"has":[206],"nice":[208],"parallel":[209],"contrastive":[211],"learning,":[212],"self-supervised":[214,293],"technique":[217],"maps":[219],"visually":[220],"data":[222,235],"points":[223],"embeddings,":[226],"where":[227],"defined":[230],"designer":[233],"through":[234,276],"augmentation":[236],"heuristics.":[237],"By":[238],"contrast,":[239],"order":[241],"use,":[248],"so":[249],"their":[253,259],"preferences":[254],"objectives,":[256],"definition":[260],"similarity.":[262],"In":[263],"simulation":[264],"user":[270],"study,":[271],"show":[273],"such":[277],"queries":[279],"leads":[280],"that,":[283],"while":[284],"far":[285],"perfect,":[287],"indeed":[289],"more":[290],"generalizable":[291],"than":[292],"task-input":[295],"alternatives.":[296]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2023-01-06T00:00:00"}