{"id":"https://openalex.org/W4285734657","doi":"https://doi.org/10.1145/3512290.3528705","title":"Approximating gradients for differentiable quality diversity in reinforcement learning","display_name":"Approximating gradients for differentiable quality diversity in reinforcement learning","publication_year":2022,"publication_date":"2022-07-08","ids":{"openalex":"https://openalex.org/W4285734657","doi":"https://doi.org/10.1145/3512290.3528705"},"language":"en","primary_location":{"id":"doi:10.1145/3512290.3528705","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3512290.3528705","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3512290.3528705","source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3512290.3528705","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007323748","display_name":"Bryon Tjanaka","orcid":null},"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"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryon Tjanaka","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]}]},{"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"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew C. Fontaine","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077267552","display_name":"Julian Togelius","orcid":"https://orcid.org/0000-0003-3128-4598"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian Togelius","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"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"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefanos Nikolaidis","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1102","last_page":"1111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9958999752998352,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9789999723434448,"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/differentiable-function","display_name":"Differentiable function","score":0.8848969340324402},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8271826505661011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7641572952270508},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6114583015441895},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5871480703353882},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5795302987098694},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.5329654216766357},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5036024451255798},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4776840806007385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4352574646472931},{"id":"https://openalex.org/keywords/current","display_name":"Current (fluid)","score":0.43275997042655945},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37864619493484497},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3521665334701538},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1534668505191803},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.12055990099906921},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.105105459690094},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06674835085868835}],"concepts":[{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.8848969340324402},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8271826505661011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641572952270508},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6114583015441895},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5871480703353882},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5795302987098694},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5329654216766357},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5036024451255798},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4776840806007385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4352574646472931},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.43275997042655945},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37864619493484497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3521665334701538},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1534668505191803},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.12055990099906921},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.105105459690094},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06674835085868835},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512290.3528705","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3512290.3528705","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3512290.3528705","source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3512290.3528705","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3512290.3528705","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3512290.3528705","source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G335962144","display_name":null,"funder_award_id":"1053128,DGE-1842487","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7461970842","display_name":null,"funder_award_id":"DGE-1842487","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8070878210","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"1842487","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8799761222","display_name":"Expansive versus contractive relational scope","funder_award_id":"1053128","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285734657.pdf","grobid_xml":"https://content.openalex.org/works/W4285734657.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1576660662","https://openalex.org/W1738827650","https://openalex.org/W1970789124","https://openalex.org/W2099746672","https://openalex.org/W2132083787","https://openalex.org/W2151083897","https://openalex.org/W2166160300","https://openalex.org/W2462548332","https://openalex.org/W2605102758","https://openalex.org/W2612085100","https://openalex.org/W2767050701","https://openalex.org/W2797210984","https://openalex.org/W2960352216","https://openalex.org/W2963157343","https://openalex.org/W2976883600","https://openalex.org/W2994369270","https://openalex.org/W3007384386","https://openalex.org/W3009840839","https://openalex.org/W3021381974","https://openalex.org/W3046002276","https://openalex.org/W3101442004","https://openalex.org/W3101747404","https://openalex.org/W3102434332","https://openalex.org/W3103183699","https://openalex.org/W3103202942","https://openalex.org/W3145430300","https://openalex.org/W3175534343","https://openalex.org/W3175814376","https://openalex.org/W3175917212","https://openalex.org/W4240805545"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2348722996","https://openalex.org/W2334570605","https://openalex.org/W3181683615","https://openalex.org/W4286826125","https://openalex.org/W1633485514","https://openalex.org/W1980454230","https://openalex.org/W2300851791","https://openalex.org/W3081644756"],"abstract_inverted_index":{"Consider":[0],"the":[1,72,98,129,138,151],"problem":[2],"of":[3,16,37,97,153],"training":[4,82],"robustly":[5],"capable":[6],"agents.":[7],"One":[8,123],"approach":[9,117],"is":[10,74,166],"to":[11,45,81,128],"generate":[12],"a":[13,25,35],"diverse":[14,42],"collection":[15,36],"agent":[17,67,83],"polices.":[18],"Training":[19],"can":[20],"then":[21],"be":[22,162],"viewed":[23],"as":[24],"quality":[26,53],"diversity":[27,54],"(QD)":[28],"optimization":[29,60],"problem,":[30],"where":[31,159],"we":[32,85],"search":[33],"for":[34,89],"performant":[38],"policies":[39,68],"that":[40,51,71,103],"are":[41,64],"with":[43],"respect":[44],"quantified":[46],"behavior.":[47,92],"Recent":[48],"work":[49],"shows":[50],"differentiable":[52],"(DQD)":[55],"algorithms":[56,80,156],"greatly":[57],"accelerate":[58],"QD":[59,134],"when":[61],"exact":[62],"gradients":[63,88,105,160],"available.":[65],"However,":[66],"typically":[69],"assume":[70],"environment":[73],"not":[75],"differentiable.":[76],"To":[77],"apply":[78],"DQD":[79,101,155],"policies,":[84],"must":[86,161],"approximate":[87],"performance":[90],"and":[91,135],"We":[93,114],"propose":[94],"two":[95,143],"variants":[96],"current":[99,130,154],"state-of-the-art":[100,131],"algorithm":[102],"compute":[104],"via":[106],"approximation":[107],"methods":[108],"common":[109],"in":[110,132,142,157],"reinforcement":[111],"learning":[112],"(RL).":[113],"evaluate":[115],"our":[116],"on":[118],"four":[119],"simulated":[120],"locomotion":[121,144],"tasks.":[122,145],"variant":[124],"achieves":[125],"results":[126,147],"comparable":[127],"combining":[133],"RL,":[136],"while":[137],"other":[139],"performs":[140],"comparably":[141],"These":[146],"provide":[148],"insight":[149],"into":[150],"limitations":[152],"domains":[158],"approximated.":[163],"Source":[164],"code":[165],"available":[167],"at":[168],"https://github.com/icaros-usc/dqd-rl":[169]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}