{"id":"https://openalex.org/W4392646009","doi":"https://doi.org/10.1145/3610978.3640692","title":"On the Pitfalls of Learning to Cooperate with Self Play Agents Checkpointed to Capture Humans of Diverse Skill Levels","display_name":"On the Pitfalls of Learning to Cooperate with Self Play Agents Checkpointed to Capture Humans of Diverse Skill Levels","publication_year":2024,"publication_date":"2024-03-10","ids":{"openalex":"https://openalex.org/W4392646009","doi":"https://doi.org/10.1145/3610978.3640692"},"language":"en","primary_location":{"id":"doi:10.1145/3610978.3640692","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3610978.3640692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","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/A5041053018","display_name":"Upasana Biswas","orcid":"https://orcid.org/0000-0003-2314-8094"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Upasana Biswas","raw_affiliation_strings":["Arizona State University, Tem, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tem, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036472369","display_name":"Lin Guan","orcid":"https://orcid.org/0009-0002-8281-8932"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin Guan","raw_affiliation_strings":["Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023323170","display_name":"Subbarao Kambhampati","orcid":"https://orcid.org/0000-0002-9069-0265"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subbarao Kambhampati","raw_affiliation_strings":["Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041053018"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02139098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"252","last_page":"256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.989300012588501,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9775000214576721,"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/adaptability","display_name":"Adaptability","score":0.7588614225387573},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6530812978744507},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6105561852455139},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.5626201033592224},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4890669286251068},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4610674977302551},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4603216052055359},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.435228168964386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4094827473163605},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3803026080131531},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11034607887268066},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07985809445381165}],"concepts":[{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.7588614225387573},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6530812978744507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6105561852455139},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.5626201033592224},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4890669286251068},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4610674977302551},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4603216052055359},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.435228168964386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4094827473163605},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3803026080131531},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11034607887268066},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07985809445381165},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3610978.3640692","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3610978.3640692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4776870722","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2980061931","https://openalex.org/W4286902222","https://openalex.org/W4394662461"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W2250140200","https://openalex.org/W3121791438"],"abstract_inverted_index":{"When":[0],"engaging":[1],"in":[2,38,113],"collaborative":[3],"tasks":[4],"with":[5,35],"unknown":[6],"team":[7],"members,":[8],"humans":[9,116],"demonstrate":[10,105],"the":[11,15,100],"ability":[12],"to":[13,22,33,115],"predict":[14],"behavior":[16],"of":[17,53,59,84,88,130],"their":[18,73,94],"partners":[19,37],"and":[20,96,117],"adapt":[21],"it.":[23],"Autonomous":[24],"agents":[25,61,85,108],"do":[26],"not":[27],"exhibit":[28,109],"such":[29,81],"adaptability,":[30],"often":[31],"struggling":[32],"integrate":[34],"new":[36],"multi-agent":[39],"cooperative":[40],"scenarios.":[41],"Past":[42],"work":[43],"towards":[44],"tackling":[45],"this":[46,76],"problem":[47],"includes":[48],"sampling":[49],"from":[50,128],"a":[51,82,118,131],"population":[52],"diverse":[54],"training":[55],"partners.":[56],"This":[57],"consists":[58],"self-play":[60,107,121],"at":[62,69],"various":[63,70],"skill":[64,90],"levels,":[65],"generated":[66],"by":[67,92],"checkpointing":[68],"points":[71],"throughout":[72],"training.":[74],"In":[75],"work,":[77],"we":[78],"show":[79],"that":[80,106,125,129],"set":[83],"isn't":[86],"representative":[87],"human":[89,133],"levels":[91],"evaluating":[93],"qualitative":[95],"quantitative":[97],"performance":[98],"on":[99],"Overcooked":[101],"Domain.":[102],"Our":[103],"results":[104],"distinct":[110],"learning":[111],"patterns":[112],"contrast":[114],"partially":[119],"trained":[120],"agent":[122],"demonstrates":[123],"behaviors":[124],"diverges":[126],"significantly":[127],"lower-skilled":[132],"counterpart.":[134]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}