{"id":"https://openalex.org/W4403430698","doi":"https://doi.org/10.1145/3638530.3654429","title":"Generating Diverse Critics for Conditioned Policy Distillation","display_name":"Generating Diverse Critics for Conditioned Policy Distillation","publication_year":2024,"publication_date":"2024-07-14","ids":{"openalex":"https://openalex.org/W4403430698","doi":"https://doi.org/10.1145/3638530.3654429"},"language":"en","primary_location":{"id":"doi:10.1145/3638530.3654429","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638530.3654429","pdf_url":null,"source":{"id":"https://openalex.org/S4363608771","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},"type":"conference-paper","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/A5054673064","display_name":"Ryan Boldi","orcid":"https://orcid.org/0000-0002-5789-0492"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Boldi","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, Massachusetts, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-5789-0492","affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, Massachusetts, United States of America","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091291769","display_name":"Matthew C. Fontaine","orcid":"https://orcid.org/0000-0002-9354-196X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Fontaine","raw_affiliation_strings":["University of Southern California, Los Angeles, California, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-9354-196X","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, California, United States of America","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037626146","display_name":"Sumeet Batra","orcid":"https://orcid.org/0009-0002-7403-0774"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumeet Batra","raw_affiliation_strings":["University of Southern California, Los Angeles, California, United States of America"],"raw_orcid":"https://orcid.org/0009-0002-7403-0774","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, California, United States of America","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077367921","display_name":"Gaurav S. Sukhatme","orcid":"https://orcid.org/0000-0003-2408-474X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Sukhatme","raw_affiliation_strings":["University of Southern California, Los Angeles, California, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-2408-474X","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, California, United States of America","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042344629","display_name":"Stefanos Nikolaidis","orcid":"https://orcid.org/0000-0002-8617-3871"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefanos Nikolaidis","raw_affiliation_strings":["University of Southern California, Los Angeles, California, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-8617-3871","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, California, United States of America","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18617483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9041000008583069,"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":0.9041000008583069,"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/distillation","display_name":"Distillation","score":0.6747559905052185},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5124738812446594},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.13091430068016052},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.06389346718788147}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6747559905052185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5124738812446594},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.13091430068016052},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.06389346718788147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3638530.3654429","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638530.3654429","pdf_url":null,"source":{"id":"https://openalex.org/S4363608771","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5959142127","display_name":"REU Site:  Robotics and Autonomous Systems","funder_award_id":"2051117","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2119717200","https://openalex.org/W2994369270","https://openalex.org/W3009840839","https://openalex.org/W3101747404","https://openalex.org/W3103183699","https://openalex.org/W3175917212","https://openalex.org/W4285734657","https://openalex.org/W4378942764","https://openalex.org/W4384008427","https://openalex.org/W4384024810"],"related_works":["https://openalex.org/W4391375266","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","https://openalex.org/W4402327032"],"abstract_inverted_index":{"Quality":[0],"Diversity":[1],"Reinforcement":[2],"Learning":[3],"(QD-RL)":[4],"allows":[5],"for":[6,33,101],"the":[7,25,82],"creation":[8],"of":[9,13,27,31,41,64,84],"a":[10,28,61,75,88,98],"large":[11,29,62],"set":[12,30],"behaviorally":[14],"diverse":[15],"yet":[16],"high":[17],"performing":[18],"policies.":[19],"However,":[20],"these":[21],"techniques":[22],"often":[23],"require":[24],"maintenance":[26],"parameters":[32],"individual":[34],"neural":[35],"network":[36],"controllers,":[37],"which":[38],"have":[39],"lots":[40],"redundancy":[42],"between":[43],"them.":[44],"In":[45],"this":[46,85,95],"work,":[47],"we":[48],"outline":[49],"and":[50,92],"test":[51],"an":[52],"approach":[53,86],"that":[54,67,94],"uses":[55],"quality":[56],"diversity":[57],"optimization":[58],"to":[59,73],"produce":[60],"archive":[63],"small":[65],"Q-functions":[66],"can":[68],"be":[69],"used":[70],"as":[71],"critics":[72],"train":[74],"larger,":[76],"task":[77],"conditioned,":[78],"policy.":[79],"We":[80],"verify":[81],"feasibility":[83],"in":[87],"maze":[89],"navigation":[90],"domain,":[91],"find":[93],"method":[96],"is":[97],"promising":[99],"technique":[100],"conditioned":[102],"policy":[103],"production.":[104]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
