{"id":"https://openalex.org/W2965993621","doi":"https://doi.org/10.1609/aaai.v33i01.33019979","title":"Deep Reinforcement Learning via Past-Success Directed Exploration","display_name":"Deep Reinforcement Learning via Past-Success Directed Exploration","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2965993621","doi":"https://doi.org/10.1609/aaai.v33i01.33019979","mag":"2965993621"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33019979","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019979","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5126/4999","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5126/4999","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100409027","display_name":"Xiaoming Liu","orcid":"https://orcid.org/0000-0002-0424-629X"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Liu","raw_affiliation_strings":["Army Engineering University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Engineering University","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072596372","display_name":"Zhixiong Xu","orcid":"https://orcid.org/0000-0003-0996-436X"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixiong Xu","raw_affiliation_strings":["Army Engineering University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Engineering University","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078602454","display_name":"Lei Cao","orcid":"https://orcid.org/0000-0002-6997-8504"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Cao","raw_affiliation_strings":["Army Engineering University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Engineering University","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030992865","display_name":"Xiliang Chen","orcid":"https://orcid.org/0000-0001-5198-0932"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiliang Chen","raw_affiliation_strings":["Army Engineering University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Engineering University","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101838715","display_name":"Kai Kang","orcid":"https://orcid.org/0000-0002-8830-0627"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Kang","raw_affiliation_strings":["Army Engineering University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Engineering University","institution_ids":["https://openalex.org/I4210163363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.10133423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"33","issue":"01","first_page":"9979","last_page":"9980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9860000014305115,"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":0.9732000231742859,"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/softmax-function","display_name":"Softmax function","score":0.9221994876861572},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8870371580123901},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6118336915969849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5185978412628174},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5081405639648438},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.464771568775177},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.4436851739883423},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42988812923431396},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42119258642196655},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3378138244152069},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.24222418665885925},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17919012904167175},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08528274297714233}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9221994876861572},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8870371580123901},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6118336915969849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5185978412628174},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5081405639648438},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.464771568775177},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.4436851739883423},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42988812923431396},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42119258642196655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3378138244152069},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.24222418665885925},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17919012904167175},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08528274297714233},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"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/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33019979","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019979","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5126/4999","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/5126","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/5126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33019979","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019979","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5126/4999","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965993621.pdf","grobid_xml":"https://content.openalex.org/works/W2965993621.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W41159429","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2561776174","https://openalex.org/W2949475445","https://openalex.org/W2963864421"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2912947802","https://openalex.org/W2037601570","https://openalex.org/W2123856982","https://openalex.org/W1530089576","https://openalex.org/W1984428377"],"abstract_inverted_index":{"The":[0,50],"balance":[1],"between":[2],"exploration":[3,19,47,82],"and":[4,60,64],"exploitation":[5],"has":[6],"always":[7],"been":[8],"a":[9],"core":[10],"challenge":[11],"in":[12],"reinforcement":[13,77],"learning.":[14],"This":[15],"paper":[16],"proposes":[17],"\u201cpast-success":[18],"strategy":[20,52,71],"combined":[21],"with":[22,58,80],"Softmax":[23],"action":[24],"selection\u201d(PSE-Softmax)":[25],"as":[26],"an":[27],"adaptive":[28],"control":[29,62],"method":[30],"for":[31],"taking":[32],"advantage":[33],"of":[34,37,42],"the":[35,38,43,65],"characteristics":[36],"online":[39],"learning":[40,78],"process":[41],"agent":[44],"to":[45],"adapt":[46],"parameters":[48],"dynamically.":[49],"proposed":[51],"is":[53],"tested":[54],"on":[55],"OpenAI":[56],"Gym":[57],"discrete":[59],"continuous":[61],"tasks,":[63],"experimental":[66],"results":[67],"show":[68],"that":[69],"PSE-Softmax":[70],"delivers":[72],"better":[73],"performance":[74],"than":[75],"deep":[76],"algorithms":[79],"basic":[81],"strategies.":[83]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}