{"id":"https://openalex.org/W2947037594","doi":"https://doi.org/10.24963/ijcai.2019/821","title":"Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies","display_name":"Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2947037594","doi":"https://doi.org/10.24963/ijcai.2019/821","mag":"2947037594"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/821","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/821","pdf_url":"https://www.ijcai.org/proceedings/2019/0821.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0821.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031617463","display_name":"Muhammad Adnan Masood","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Muhammad Masood","raw_affiliation_strings":["Harvard University","Harvard University ,"],"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038771285","display_name":"Finale Doshi\u2010Velez","orcid":"https://orcid.org/0000-0003-2886-3898"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Finale Doshi-Velez","raw_affiliation_strings":["Harvard University","Harvard University ,"],"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031617463"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":1.0116,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82482779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5923","last_page":"5929"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9926000237464905,"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":0.9926000237464905,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9879000186920166,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9819999933242798,"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/diversity","display_name":"Diversity (politics)","score":0.7795028686523438},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7082082033157349},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6984413266181946},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6286946535110474},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6142992973327637},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.507021427154541},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4901336133480072},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.42969974875450134},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.42942166328430176},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3650076389312744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3205103278160095},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28305819630622864},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.24590346217155457},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.13635995984077454},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.07639610767364502},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06504243612289429}],"concepts":[{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.7795028686523438},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7082082033157349},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6984413266181946},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6286946535110474},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6142992973327637},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.507021427154541},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4901336133480072},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.42969974875450134},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.42942166328430176},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3650076389312744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3205103278160095},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28305819630622864},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.24590346217155457},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.13635995984077454},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07639610767364502},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06504243612289429},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2019/821","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/821","pdf_url":"https://www.ijcai.org/proceedings/2019/0821.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.00088","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.00088","pdf_url":"https://arxiv.org/pdf/1906.00088","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"},{"id":"doi:10.48550/arxiv.1906.00088","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.00088","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:2947037594","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/821","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/821","pdf_url":"https://www.ijcai.org/proceedings/2019/0821.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5299999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2947037594.pdf","grobid_xml":"https://content.openalex.org/works/W2947037594.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W1898928487","https://openalex.org/W1987725948","https://openalex.org/W2011861268","https://openalex.org/W2104733512","https://openalex.org/W2110097068","https://openalex.org/W2121506959","https://openalex.org/W2125865219","https://openalex.org/W2128349740","https://openalex.org/W2151083897","https://openalex.org/W2153484303","https://openalex.org/W2155027007","https://openalex.org/W2159272820","https://openalex.org/W2575572349","https://openalex.org/W2594103415","https://openalex.org/W2604373826","https://openalex.org/W2606757878","https://openalex.org/W2736601468","https://openalex.org/W2739341730","https://openalex.org/W2757504960","https://openalex.org/W2785720656","https://openalex.org/W2785940258","https://openalex.org/W2803839069","https://openalex.org/W2896893468","https://openalex.org/W2962839548","https://openalex.org/W2963400359","https://openalex.org/W2963438456","https://openalex.org/W2963906781","https://openalex.org/W2964174623"],"related_works":["https://openalex.org/W2966128956","https://openalex.org/W3123720267","https://openalex.org/W2000975201","https://openalex.org/W3112404509","https://openalex.org/W2103098029","https://openalex.org/W2977099601","https://openalex.org/W2620289825","https://openalex.org/W3209343152","https://openalex.org/W3088484880","https://openalex.org/W3160600403","https://openalex.org/W3110568267","https://openalex.org/W3167790141","https://openalex.org/W2964297722","https://openalex.org/W3098679278","https://openalex.org/W2952561542","https://openalex.org/W3081226161","https://openalex.org/W2910781732","https://openalex.org/W3175189009","https://openalex.org/W1784395471","https://openalex.org/W2007113996"],"abstract_inverted_index":{"Standard":[0],"reinforcement":[1],"learning":[2],"methods":[3,108],"aim":[4],"to":[5,22,34,54,87,109],"master":[6],"one":[7],"way":[8],"of":[9,26,39,76,114],"solving":[10],"a":[11,31,71,96,124],"task":[12],"whereas":[13],"there":[14],"may":[15],"exist":[16],"multiple":[17],"near-optimal":[18,27],"policies.":[19,116],"Being":[20],"able":[21],"identify":[23,111],"this":[24,62],"collection":[25],"policies":[28,49,56,69],"can":[29,101],"allow":[30],"domain":[32],"expert":[33],"efficiently":[35],"explore":[36],"the":[37,66,74],"space":[38],"reasonable":[40],"solutions.":[41],"Unfortunately,":[42],"existing":[43,105],"approaches":[44],"that":[45,100],"quantify":[46],"uncertainty":[47],"over":[48],"are":[50],"not":[51],"ultimately":[52],"relevant":[53],"finding":[55],"with":[57,85,104],"qualitatively":[58],"distinct":[59],"behaviors.":[60],"In":[61],"work,":[63],"we":[64],"formalize":[65],"difference":[67,72],"between":[68,73],"as":[70],"distribution":[75],"trajectories":[77],"induced":[78],"by":[79],"each":[80],"policy,":[81],"which":[82],"encourages":[83],"diversity":[84],"respect":[86],"both":[88],"state":[89],"visitation":[90],"and":[91,123],"action":[92],"choices.":[93],"We":[94,117],"derive":[95],"gradient-based":[97],"optimization":[98],"technique":[99],"be":[102],"combined":[103],"policy":[106],"gradient":[107],"now":[110],"diverse":[112],"collections":[113],"well-performing":[115],"demonstrate":[118],"our":[119],"approach":[120],"on":[121],"benchmarks":[122],"healthcare":[125],"task.":[126]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}