{"id":"https://openalex.org/W4285782692","doi":"https://doi.org/10.1145/3356464.3357706","title":"Generative adversarial exploration for reinforcement learning","display_name":"Generative adversarial exploration for reinforcement learning","publication_year":2019,"publication_date":"2019-10-13","ids":{"openalex":"https://openalex.org/W4285782692","doi":"https://doi.org/10.1145/3356464.3357706"},"language":"en","primary_location":{"id":"doi:10.1145/3356464.3357706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3356464.3357706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Conference on Distributed Artificial Intelligence","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/A5107771481","display_name":"Weijun Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weijun Hong","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034417837","display_name":"Menghui Zhu","orcid":"https://orcid.org/0000-0002-8567-2185"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menghui Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101433372","display_name":"Minghuan Liu","orcid":"https://orcid.org/0009-0009-5585-1746"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghuan Liu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090720315","display_name":"Weinan Zhang","orcid":"https://orcid.org/0000-0002-0127-2425"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weinan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701574","display_name":"Ming Zhou","orcid":"https://orcid.org/0000-0002-5701-1996"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001571390","display_name":"Yong Yu","orcid":"https://orcid.org/0000-0003-0281-8271"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Yu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101404135","display_name":"Peng Sun","orcid":"https://orcid.org/0000-0002-8187-9736"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Sun","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5107771481"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.68934828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9941999912261963,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/discriminator","display_name":"Discriminator","score":0.9032722115516663},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.898196816444397},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8469066619873047},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.770210862159729},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.694068431854248},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6924748420715332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6369004249572754},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6122123003005981},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6038569808006287},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5410451292991638},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5224751234054565},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5186492800712585},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15699061751365662},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08467218279838562},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.06183329224586487}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9032722115516663},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.898196816444397},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8469066619873047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770210862159729},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.694068431854248},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6924748420715332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6369004249572754},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6122123003005981},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6038569808006287},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5410451292991638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5224751234054565},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5186492800712585},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15699061751365662},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08467218279838562},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.06183329224586487},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3356464.3357706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3356464.3357706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Conference on Distributed Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1575592356","https://openalex.org/W1863227302","https://openalex.org/W1988526405","https://openalex.org/W2000514530","https://openalex.org/W2020920737","https://openalex.org/W2034806191","https://openalex.org/W2082691056","https://openalex.org/W2124352385","https://openalex.org/W2145339207","https://openalex.org/W2963523627","https://openalex.org/W4214717370","https://openalex.org/W6658934047"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W4380714744","https://openalex.org/W2387995142","https://openalex.org/W4319453655","https://openalex.org/W2057775761","https://openalex.org/W2964074194","https://openalex.org/W2089959425","https://openalex.org/W2995777218"],"abstract_inverted_index":{"Exploration":[0],"is":[1,14,21,39,100,109,117,166],"crucial":[2],"for":[3],"training":[4,124],"the":[5,12,81,98,107,135,146,167],"optimal":[6],"reinforcement":[7],"learning":[8,160],"(RL)":[9],"policy,":[10],"where":[11,80],"key":[13],"to":[15,34,64,102,112,119,170],"discriminate":[16],"whether":[17,36],"a":[18,37,44,56,76],"state":[19,38],"visiting":[20],"novel.":[22],"Most":[23],"previous":[24],"work":[25,169],"focuses":[26],"on":[27,141,158],"designing":[28],"heuristic":[29],"rules":[30],"or":[31],"distance":[32],"metrics":[33],"check":[35],"novel":[40,57],"without":[41,155],"considering":[42],"such":[43],"discrimination":[45],"process":[46],"that":[47,88],"can":[48],"be":[49],"learned.":[50],"In":[51,126],"this":[52,165],"paper,":[53],"we":[54,129],"propose":[55],"method":[58],"called":[59],"generative":[60,77],"adversarial":[61,78],"exploration":[62,66,143,175],"(GAEX)":[63],"encourage":[65],"in":[67,173],"RL":[68,174],"via":[69],"introducing":[70],"an":[71],"intrinsic":[72],"reward":[73],"output":[74],"from":[75],"network,":[79],"generator":[82],"provides":[83],"fake":[84],"samples":[85],"of":[86,122],"states":[87,105],"help":[89],"discriminator":[90,108],"identify":[91],"those":[92,104],"less":[93,110],"frequently":[94],"visited":[95],"states.":[96],"Thus":[97],"agent":[99],"encouraged":[101],"visit":[103],"which":[106],"confident":[111],"judge":[113],"as":[114],"visited.":[115],"GAEX":[116,131],"easy":[118],"implement":[120],"and":[121,134,151],"high":[123],"efficiency.":[125],"our":[127,163],"experiments,":[128],"apply":[130],"into":[132],"DQN":[133],"DQN-GAEX":[136],"algorithm":[137],"achieves":[138],"convincing":[139],"performance":[140],"challenging":[142],"problems,":[144],"including":[145],"game":[147],"Venture,":[148],"Montezuma's":[149],"Revenge":[150],"Super":[152],"Mario":[153],"Bros,":[154],"further":[156],"fine-tuning":[157],"complicate":[159],"algorithms.":[161],"To":[162],"knowledge,":[164],"first":[168],"employ":[171],"GAN":[172],"problems.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}