{"id":"https://openalex.org/W3129745895","doi":"https://doi.org/10.48550/arxiv.2104.02871","title":"On the Critical Role of Conventions in Adaptive Human-AI Collaboration","display_name":"On the Critical Role of Conventions in Adaptive Human-AI Collaboration","publication_year":2021,"publication_date":"2021-04-07","ids":{"openalex":"https://openalex.org/W3129745895","doi":"https://doi.org/10.48550/arxiv.2104.02871","mag":"3129745895"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2104.02871","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02871","pdf_url":"https://arxiv.org/pdf/2104.02871","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.02871","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065371323","display_name":"Andy Shih","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shih, Andy","raw_affiliation_strings":["Princeton University","Computer Science Department, Stanford University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Computer Science Department, Stanford University,","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068269107","display_name":"Arjun Sawhney","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sawhney, Arjun","raw_affiliation_strings":["Princeton University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045938069","display_name":"Jovana Kondic","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kondic, Jovana","raw_affiliation_strings":["Stanford University ,","Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University ,","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091179481","display_name":"Stefano Ermon","orcid":"https://orcid.org/0000-0003-0039-2887","observed_orcids":["https://orcid.org/0000-0003-0039-2887"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ermon, Stefano","raw_affiliation_strings":["Princeton University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080725225","display_name":"Dorsa Sadigh","orcid":"https://orcid.org/0000-0002-7802-9183","observed_orcids":["https://orcid.org/0000-0002-7802-9183"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sadigh, Dorsa","raw_affiliation_strings":["Princeton University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":null,"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":0.6381999850273132,"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":0.6381999850273132,"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":0.09030000120401382,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.023600000888109207,"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/human-ai-collaboration","display_name":"human-AI collaboration","score":0.9459999799728394},{"id":"https://openalex.org/keywords/convention","display_name":"convention","score":0.5989999771118164},{"id":"https://openalex.org/keywords/adaptive-agents","display_name":"adaptive agents","score":0.4309999942779541},{"id":"https://openalex.org/keywords/zero-shot-transfer","display_name":"zero-shot transfer","score":0.5929999947547913},{"id":"https://openalex.org/keywords/best-response-strategies","display_name":"best response strategy","score":0.8539999723434448},{"id":"https://openalex.org/keywords/multi-armed-bandits","display_name":"multi-armed bandits","score":0.6759999990463257},{"id":"https://openalex.org/keywords/hanabi","display_name":"Hanabi","score":0.8939999938011169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759110689163208},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6007921099662781},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5811870098114014},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5443983674049377},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.523967981338501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42680680751800537},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.41887959837913513},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2104.02871","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02871","pdf_url":"https://arxiv.org/pdf/2104.02871","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"mag:3151072864","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2104.02871","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.02871","doi":"https://doi.org/10.48550/arxiv.2104.02871","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.02871","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3129745895","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=8Ln-Bq0mZcy","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.02871","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02871","pdf_url":"https://arxiv.org/pdf/2104.02871","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6022427645","display_name":"CAREER: Safe and Influencing Interactions for Human-Robot Systems","funder_award_id":"1941722","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6724297927","display_name":"CHS: Small: Learning and Leveraging Conventions in Human-Robot Interaction","funder_award_id":"2006388","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/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1521003796","https://openalex.org/W1606056663","https://openalex.org/W2068038882","https://openalex.org/W2085837954","https://openalex.org/W2098774185","https://openalex.org/W2142947219","https://openalex.org/W2525032226","https://openalex.org/W2526379199","https://openalex.org/W2594035753","https://openalex.org/W2736601468","https://openalex.org/W2777660616","https://openalex.org/W2786533521","https://openalex.org/W2788266634","https://openalex.org/W2806117557","https://openalex.org/W2911616846","https://openalex.org/W2913340405","https://openalex.org/W2913781869","https://openalex.org/W2922252999","https://openalex.org/W2950472486","https://openalex.org/W2962808690","https://openalex.org/W2963627051","https://openalex.org/W2963881016","https://openalex.org/W2970894611","https://openalex.org/W2972695646","https://openalex.org/W2973525135","https://openalex.org/W2993490502","https://openalex.org/W3009741087","https://openalex.org/W3037911642","https://openalex.org/W3104860527"],"related_works":["https://openalex.org/W7221161773","https://openalex.org/W4388275994","https://openalex.org/W7162416804","https://openalex.org/W4415971853","https://openalex.org/W4417201935","https://openalex.org/W4414360435","https://openalex.org/W7133265583","https://openalex.org/W7155008773","https://openalex.org/W7162411400","https://openalex.org/W4416516320"],"abstract_inverted_index":{"Humans":[0,34],"can":[1,35],"quickly":[2,37,76,175],"adapt":[3,38,75,174],"to":[4,24,27,39,63,77,91,97,120,173,176,180],"new":[5,32,78,81,121,177,186],"partners":[6,45,79,184],"in":[7,139,188,202],"collaborative":[8,199],"tasks":[9,41,82,187,200],"(e.g.":[10,22,54],"playing":[11],"basketball),":[12],"because":[13],"they":[14,51],"understand":[15],"which":[16],"fundamental":[17],"skills":[18],"of":[19,156,167],"the":[20,43,59,94,101,157,213],"task":[21,99],"how":[23,26],"dribble,":[25],"shoot)":[28],"carry":[29],"over":[30,48,159],"across":[31,162],"partners.":[33,163],"also":[36],"similar":[40],"with":[42,70,182],"same":[44],"by":[46,104],"carrying":[47],"conventions":[49,102,117],"that":[50,131],"have":[52,88],"developed":[53],"raising":[55],"hand":[56],"signals":[57],"pass":[58],"ball),":[60],"without":[61],"learning":[62,129],"coordinate":[64,181],"from":[65,136],"scratch.":[66],"To":[67],"collaborate":[68],"seamlessly":[69],"humans,":[71],"AI":[72],"agents":[73,170],"should":[74],"and":[80,100,107,179,212],"as":[83],"well.":[84],"However,":[85],"current":[86],"approaches":[87],"not":[89],"attempted":[90],"distinguish":[92],"between":[93],"complexities":[95],"intrinsic":[96],"a":[98,105,128,140,153,189,204,208],"used":[103],"partner,":[106],"more":[108],"generally":[109],"there":[110],"has":[111],"been":[112],"little":[113],"focus":[114],"on":[115,185,197],"leveraging":[116],"for":[118],"adapting":[119],"settings.":[122],"In":[123],"this":[124,165],"work,":[125],"we":[126],"propose":[127],"framework":[130],"teases":[132],"apart":[133],"rule-dependent":[134,150],"representation":[135,138,151],"convention-dependent":[137],"principled":[141],"way.":[142],"We":[143,192],"show":[144],"that,":[145],"under":[146],"some":[147],"assumptions,":[148],"our":[149,169,195],"is":[152],"sufficient":[154],"statistic":[155],"distribution":[158],"best-response":[160],"strategies":[161],"Using":[164],"separation":[166],"representations,":[168],"are":[171],"able":[172],"partners,":[178],"old":[183],"zero-shot":[190],"manner.":[191],"experimentally":[193],"validate":[194],"approach":[196],"three":[198],"varying":[201],"complexity:":[203],"contextual":[205],"multi-armed":[206],"bandit,":[207],"block":[209],"placing":[210],"task,":[211],"card":[214],"game":[215],"Hanabi.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-03-01T00:00:00"}