{"id":"https://openalex.org/W4390446699","doi":"https://doi.org/10.1145/3627676.3627687","title":"Backtracking Exploration for Reinforcement Learning","display_name":"Backtracking Exploration for Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-30","ids":{"openalex":"https://openalex.org/W4390446699","doi":"https://doi.org/10.1145/3627676.3627687"},"language":"en","primary_location":{"id":"doi:10.1145/3627676.3627687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627676.3627687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Fifth 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/A5025828195","display_name":"Xingguo Chen","orcid":"https://orcid.org/0000-0002-0221-733X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingguo Chen","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030259119","display_name":"Zening Chen","orcid":"https://orcid.org/0000-0002-2266-7776"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zening Chen","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088206029","display_name":"Dingyuanhao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingyuanhao Sun","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18292501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9921000003814697,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8563857078552246},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6960024833679199},{"id":"https://openalex.org/keywords/backtracking","display_name":"Backtracking","score":0.6498557329177856},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5754186511039734},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.531541109085083},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5254120826721191},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5225474238395691},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.47743162512779236},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45855826139450073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4258822202682495},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4135197103023529},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4111734628677368},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21730604767799377},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15412503480911255}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8563857078552246},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6960024833679199},{"id":"https://openalex.org/C156884757","wikidata":"https://www.wikidata.org/wiki/Q798554","display_name":"Backtracking","level":2,"score":0.6498557329177856},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5754186511039734},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.531541109085083},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5254120826721191},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5225474238395691},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.47743162512779236},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45855826139450073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4258822202682495},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4135197103023529},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4111734628677368},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21730604767799377},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15412503480911255},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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:10.1145/3627676.3627687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627676.3627687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Fifth International Conference on Distributed Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6820656122","display_name":null,"funder_award_id":"62276142, 62206133, 62202240, 62192783","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1547925194","https://openalex.org/W1600006923","https://openalex.org/W1646707810","https://openalex.org/W2100677568","https://openalex.org/W2121863487","https://openalex.org/W2168405694","https://openalex.org/W2531563875","https://openalex.org/W2912083425","https://openalex.org/W2990138404","https://openalex.org/W3009585715","https://openalex.org/W3034039613","https://openalex.org/W3090826728","https://openalex.org/W3160259219","https://openalex.org/W3196183762","https://openalex.org/W3207876914","https://openalex.org/W3214682039","https://openalex.org/W4307347247","https://openalex.org/W6677826109","https://openalex.org/W6784003830"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W2742483371","https://openalex.org/W3038962357","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3099153698","https://openalex.org/W3087814763","https://openalex.org/W2025663273"],"abstract_inverted_index":{"Exploration":[0],"of":[1,33,39,46,53,57,96,105,165],"the":[2,31,37,47,51,54,58,64,74,83,90,93,97,106,114,146,154,163,166],"behavior":[3],"policy":[4,85],"plays":[5],"an":[6,26],"important":[7],"role":[8],"in":[9,113,157],"reinforcement":[10,158],"learning":[11,15],"as":[12,25],"it":[13,144],"helps":[14],"algorithms":[16],"escape":[17],"local":[18],"optima.":[19],"Taking":[20],"linear":[21],"value":[22,139],"function":[23,140],"approximation":[24],"example,":[27],"exploration":[28,69,121,136],"directly":[29,132],"affects":[30],"sampling":[32],"states,":[34],"thereby":[35],"altering":[36],"distribution":[38,42],"states.":[40],"This":[41,87,128],"is":[43,61],"a":[44,119,150],"component":[45],"key":[48,59],"matrix,":[49],"and":[50,77,117,126,138,143],"magnitude":[52],"smallest":[55],"eigenvalue":[56],"matrix":[60],"proportional":[62],"to":[63,81,103,148],"convergence":[65],"speed.":[66],"However,":[67],"existing":[68,135],"methods":[70],"are":[71],"constrained":[72],"by":[73,109],"MDP":[75],"chain":[76],"require":[78],"step-by-step":[79],"backtracking":[80,120],"reach":[82],"target":[84],"distribution.":[86],"paper":[88],"breaks":[89],"assumption":[91],"that":[92,104],"action":[94],"settings":[95],"training":[98,115,155],"environment":[99,108,116],"must":[100],"be":[101,131],"identical":[102],"testing":[107],"introducing":[110],"state":[111],"resetting":[112],"proposes":[118],"algorithm":[122,129],"with":[123,134],"time":[124],"window":[125],"punishment.":[127],"can":[130],"combined":[133],"strategies":[137],"update":[141],"rules,":[142],"has":[145],"potential":[147],"become":[149],"new":[151],"paradigm":[152],"for":[153],"process":[156],"learning.":[159],"Experimental":[160],"results":[161],"validate":[162],"effectiveness":[164],"proposed":[167],"algorithm.":[168]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}