{"id":"https://openalex.org/W2998168154","doi":"https://doi.org/10.1145/3319502.3374791","title":"Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation","display_name":"Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation","publication_year":2020,"publication_date":"2020-03-07","ids":{"openalex":"https://openalex.org/W2998168154","doi":"https://doi.org/10.1145/3319502.3374791","mag":"2998168154"},"language":"en","primary_location":{"id":"doi:10.1145/3319502.3374791","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3319502.3374791","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3319502.3374791","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3319502.3374791","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Letian Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Letian Chen","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rohan Paleja","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohan Paleja","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Muyleng Ghuy","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muyleng Ghuy","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":null,"display_name":"Matthew Gombolay","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Gombolay","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.9199,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.77898871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"659","last_page":"668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9969000220298767,"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":0.9969000220298767,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9545000195503235,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9538000226020813,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7300000190734863},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6409000158309937},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5579000115394592},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5475000143051147},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.541700005531311},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4198000133037567},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.35580000281333923}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7300000190734863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245000004768372},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6409000158309937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5879999995231628},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5579000115394592},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5475000143051147},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.541700005531311},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4797999858856201},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C143661069","wikidata":"https://www.wikidata.org/wiki/Q670713","display_name":"Reward system","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3319502.3374791","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3319502.3374791","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3319502.3374791","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.00503","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.00503","pdf_url":"https://arxiv.org/pdf/2001.00503","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,"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:10.1145/3319502.3374791","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3319502.3374791","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3319502.3374791","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4375267691","display_name":null,"funder_award_id":"N00014-18-S-B001","funder_id":"https://openalex.org/F4320338298","funder_display_name":"Office of Naval Research Global"},{"id":"https://openalex.org/G6438257714","display_name":null,"funder_award_id":"7000437192","funder_id":"https://openalex.org/F4320332503","funder_display_name":"Lincoln Laboratory, Massachusetts Institute of Technology"},{"id":"https://openalex.org/G67361369","display_name":null,"funder_award_id":"N00014-18-S-B001","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320332503","display_name":"Lincoln Laboratory, Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44"},{"id":"https://openalex.org/F4320332869","display_name":"College of Computing","ror":"https://ror.org/01zkghx44"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338298","display_name":"Office of Naval Research Global","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2998168154.pdf","grobid_xml":"https://content.openalex.org/works/W2998168154.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1591675293","https://openalex.org/W1999874108","https://openalex.org/W2149167871","https://openalex.org/W2153894094","https://openalex.org/W2158782408","https://openalex.org/W2166353350","https://openalex.org/W2169498096","https://openalex.org/W2618170641","https://openalex.org/W2765726432","https://openalex.org/W2770884134","https://openalex.org/W2809814728","https://openalex.org/W6682849425","https://openalex.org/W6738860160","https://openalex.org/W6740879895"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,12,38,89],"(RL)":[2],"has":[3],"achieved":[4],"tremendous":[5],"success":[6,19],"as":[7],"a":[8,26,43,112,117,133,169],"general":[9],"framework":[10],"for":[11],"how":[13],"to":[14,41,95,102,114,131,141],"make":[15],"decisions.":[16],"However,":[17],"this":[18,108],"relies":[20],"on":[21],"the":[22,33,96,104,162],"interactive":[23],"hand-tuning":[24],"of":[25,66],"reward":[27,44,58,68,136,138,156],"function":[28,45],"by":[29],"RL":[30],"experts.":[31],"On":[32],"other":[34],"hand,":[35],"inverse":[36],"reinforcement":[37],"(IRL)":[39],"seeks":[40,101],"learn":[42],"from":[46,53,90],"readily-obtained":[47],"human":[48,80],"demonstrations.":[49],"Yet,":[50],"IRL":[51],"suffers":[52],"two":[54,165],"major":[55],"limitations:":[56],"1)":[57],"ambiguity":[59],"-":[60,79],"there":[61],"are":[62],"an":[63,73],"infinite":[64],"number":[65],"possible":[67],"functions":[69],"that":[70,99],"could":[71],"explain":[72],"expert's":[74],"demonstration":[75],"and":[76,85,120,140,157,160,168],"2)":[77],"heterogeneity":[78],"experts":[81],"adopt":[82],"varying":[83],"strategies":[84,163],"preferences,":[86],"which":[87],"makes":[88],"multiple":[91],"demonstrators":[92,100],"difficult":[93],"due":[94],"common":[97],"assumption":[98],"maximize":[103],"same":[105],"reward.":[106],"In":[107],"work,":[109],"we":[110],"propose":[111],"method":[113],"jointly":[115],"infer":[116],"task":[118,135,155],"goal":[119],"humans'":[121],"strategic":[122],"preferences":[123],"via":[124],"network":[125],"distillation.":[126],"This":[127],"approach":[128],"enables":[129],"us":[130],"distill":[132],"robust":[134],"(addressing":[137],"ambiguity)":[139],"model":[142],"each":[143],"strategy's":[144],"objective":[145],"(handling":[146],"heterogeneity).":[147],"We":[148],"demonstrate":[149],"our":[150],"algorithm":[151],"can":[152],"better":[153],"recover":[154],"strategy":[158],"rewards":[159],"imitate":[161],"in":[164],"simulated":[166],"tasks":[167],"real-world":[170],"table":[171],"tennis":[172],"task.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2020-01-10T00:00:00"}