{"id":"https://openalex.org/W2963024489","doi":null,"title":"Parameter Space Noise for Exploration","display_name":"Parameter Space Noise for Exploration","publication_year":2018,"publication_date":"2018-02-15","ids":{"openalex":"https://openalex.org/W2963024489","mag":"2963024489"},"language":"en","primary_location":{"id":"mag:2963024489","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=ByBAl2eAZ","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5037117755","display_name":"Matthias Plappert","orcid":"https://orcid.org/0000-0002-0751-8094","observed_orcids":["https://orcid.org/0000-0002-0751-8094"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthias Plappert","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0751-8094","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003630193","display_name":"Rein Houthooft","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rein Houthooft","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076418776","display_name":"Prafulla Dhariwal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prafulla Dhariwal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051574174","display_name":"Szymon Sidor","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szymon Sidor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005243537","display_name":"Richard Y. Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard Y. Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-3135-4114","observed_orcids":["https://orcid.org/0000-0002-3135-4114"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3135-4114","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012730104","display_name":"Tamim Asfour","orcid":"https://orcid.org/0000-0003-4879-7680","observed_orcids":["https://orcid.org/0000-0003-4879-7680"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tamim Asfour","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4879-7680","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":"https://orcid.org/0009-0007-0628-9932","observed_orcids":["https://orcid.org/0009-0007-0628-9932"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091819924","display_name":"Marcin Andrychowicz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcin Andrychowicz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.4587,"has_fulltext":false,"cited_by_count":90,"citation_normalized_percentile":{"value":0.97755857,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.9179999828338623},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.9139999747276306},{"id":"https://openalex.org/keywords/evolution-strategies","display_name":"evolution strategies","score":0.9139999747276306},{"id":"https://openalex.org/keywords/parameter-perturbation","display_name":"parameter perturbation","score":0.7120000123977661},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.6959999799728394},{"id":"https://openalex.org/keywords/ddpg","display_name":"deep deterministic policy gradient","score":0.9990000128746033},{"id":"https://openalex.org/keywords/trialkylphosphine-oxide","display_name":"TRPO","score":0.984000027179718},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":1.0}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8355110287666321},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7807337045669556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6973764896392822},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6115872263908386},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.5624071955680847},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5602965950965881},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5495889186859131},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.518587589263916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49463364481925964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35162389278411865},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21545597910881042},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07903903722763062},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07568246126174927},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2963024489","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=ByBAl2eAZ","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2906292189","https://openalex.org/W2890105054","https://openalex.org/W2142916680","https://openalex.org/W7127656696","https://openalex.org/W3153965298","https://openalex.org/W7099619944","https://openalex.org/W4281784898","https://openalex.org/W3035189581","https://openalex.org/W4206024271","https://openalex.org/W3037231457"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"methods":[4,68,84],"generally":[5],"engage":[6],"in":[7,13,54],"exploratory":[8],"behavior":[9],"through":[10,89],"noise":[11,22,64,115,125],"injection":[12],"the":[14,25,55,72],"action":[15,100,123],"space.":[16],"An":[17],"alternative":[18],"is":[19],"to":[20,24,31,70],"add":[21],"directly":[23],"agent's":[26],"parameters,":[27],"which":[28],"can":[29],"lead":[30],"more":[32,60,117],"consistent":[33],"exploration":[34],"and":[35,57,82,95,126],"a":[36],"richer":[37],"set":[38],"of":[39,74,92],"behaviors.":[40],"Methods":[41],"such":[42],"as":[43,102,104],"evolutionary":[44,127],"strategies":[45,128],"use":[46],"parameter":[47,63,114],"perturbations,":[48],"but":[49],"discard":[50],"all":[51],"temporal":[52],"structure":[53],"process":[56],"require":[58],"significantly":[59],"samples.":[61],"Combining":[62],"with":[65,113,122],"traditional":[66,120],"RL":[67,112,121],"allows":[69],"combine":[71],"best":[73],"both":[75,80],"worlds.":[76],"We":[77],"demonstrate":[78],"that":[79,111],"off-":[81],"on-policy":[83],"benefit":[85],"from":[86],"this":[87],"approach":[88],"experimental":[90],"comparison":[91],"DQN,":[93],"DDPG,":[94],"TRPO":[96],"on":[97],"high-dimensional":[98],"discrete":[99],"environments":[101],"well":[103],"continuous":[105],"control":[106],"tasks.":[107],"Our":[108],"results":[109],"show":[110],"learns":[116],"efficiently":[118],"than":[119],"space":[124],"individually.":[129]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":14},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-07-30T00:00:00"}