{"id":"https://openalex.org/W3177807326","doi":"https://doi.org/10.1145/3449726.3459462","title":"Reinforcement learning with rare significant events","display_name":"Reinforcement learning with rare significant events","publication_year":2021,"publication_date":"2021-07-07","ids":{"openalex":"https://openalex.org/W3177807326","doi":"https://doi.org/10.1145/3449726.3459462","mag":"3177807326"},"language":"en","primary_location":{"id":"doi:10.1145/3449726.3459462","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3449726.3459462","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":"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/A5008969852","display_name":"Paul Ecoffet","orcid":"https://orcid.org/0000-0002-7394-6134"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Paul Ecoffet","raw_affiliation_strings":["Sorbonne Universit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014203087","display_name":"Nicolas Fontbonne","orcid":"https://orcid.org/0009-0001-4948-905X"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Fontbonne","raw_affiliation_strings":["Sorbonne Universit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040122774","display_name":"Jean\u2010Baptiste Andr\u00e9","orcid":"https://orcid.org/0000-0001-9069-447X"},"institutions":[{"id":"https://openalex.org/I4210162280","display_name":"Laboratoire de G\u00e9ologie de l\u2019\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/05vg9cw43","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210148025","https://openalex.org/I4210162280"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Baptiste Andr\u00e9","raw_affiliation_strings":["\u00c9cole Normale Sup\u00e9rieure, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole Normale Sup\u00e9rieure, Paris, France","institution_ids":["https://openalex.org/I4210162280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008211251","display_name":"Nicolas Bred\u00e8che","orcid":"https://orcid.org/0000-0002-8241-7461"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Bredeche","raw_affiliation_strings":["Sorbonne Universit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1268,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.33207024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"98"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10603","display_name":"Smart Grid Energy Management","score":0.9769999980926514,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9011764526367188},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.747146725654602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6840754747390747},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6788774728775024},{"id":"https://openalex.org/keywords/rare-events","display_name":"Rare events","score":0.593097984790802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47370976209640503},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.42718130350112915},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3591841459274292},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13848671317100525},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11398789286613464},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07184472680091858},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07109495997428894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06458750367164612}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9011764526367188},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.747146725654602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840754747390747},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6788774728775024},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.593097984790802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47370976209640503},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.42718130350112915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3591841459274292},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13848671317100525},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11398789286613464},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07184472680091858},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07109495997428894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06458750367164612},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3449726.3459462","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3449726.3459462","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/G7227267978","display_name":"Morpho-functional Swarm Robotics","funder_award_id":"ANR-18-CE33-0006","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2098152875","https://openalex.org/W2167019781","https://openalex.org/W2565313327","https://openalex.org/W2962930448","https://openalex.org/W3134329363","https://openalex.org/W3177807326"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W1914583973","https://openalex.org/W2130711276","https://openalex.org/W4308828368"],"abstract_inverted_index":{"This":[0],"paper":[1],"shows":[2],"that":[3],"the":[4],"CMAES":[5],"direct":[6],"policy":[7,16],"search":[8,17],"method":[9],"fares":[10],"significantly":[11],"better":[12],"than":[13],"PPO":[14],"gradient":[15],"for":[18],"a":[19],"reinforcement":[20],"learning":[21],"task":[22],"where":[23],"significant":[24],"events":[25],"are":[26],"rare.":[27]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}
