{"id":"https://openalex.org/W4399173338","doi":"https://doi.org/10.1145/3660043.3660202","title":"Enhancing Curiosity-driven Reinforcement Learning through Historical State Information for Long-term Exploration","display_name":"Enhancing Curiosity-driven Reinforcement Learning through Historical State Information for Long-term Exploration","publication_year":2023,"publication_date":"2023-12-22","ids":{"openalex":"https://openalex.org/W4399173338","doi":"https://doi.org/10.1145/3660043.3660202"},"language":"en","primary_location":{"id":"doi:10.1145/3660043.3660202","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3660043.3660202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 International Conference on Information Education and 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/A5036274103","display_name":"J. Y. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Wang","raw_affiliation_strings":["School of Optics and Photonics, Beijing Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Optics and Photonics, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091007362","display_name":"Bo Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["School of Optics and Photonics, Beijing Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Optics and Photonics, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005235154","display_name":"Jing Chen","orcid":"https://orcid.org/0000-0002-9503-6430"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chen","raw_affiliation_strings":["School of Optics and Photonics, Beijing Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Optics and Photonics, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102934605","display_name":"Ting Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Lei","raw_affiliation_strings":["School of Optics and Photonics, Beijing Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Optics and Photonics, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004611193","display_name":"Ke Ni","orcid":"https://orcid.org/0009-0004-4329-8027"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Ni","raw_affiliation_strings":["School of Optics and Photonics, Beijing Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Optics and Photonics, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036274103"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21431228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"897","last_page":"902"},"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":0.9904000163078308,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9854999780654907,"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/curiosity","display_name":"Curiosity","score":0.965238630771637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7511062026023865},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6843549013137817},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5649209022521973},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5127154588699341},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48859983682632446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48670533299446106},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.47369953989982605},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41563525795936584},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40854427218437195},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11881068348884583},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09348958730697632}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.965238630771637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7511062026023865},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6843549013137817},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5649209022521973},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5127154588699341},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48859983682632446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48670533299446106},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.47369953989982605},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41563525795936584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40854427218437195},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11881068348884583},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09348958730697632},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems 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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3660043.3660202","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3660043.3660202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 International Conference on Information Education and 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":15,"referenced_works":["https://openalex.org/W1547295060","https://openalex.org/W2060422862","https://openalex.org/W2150468603","https://openalex.org/W2173248099","https://openalex.org/W2724169821","https://openalex.org/W2736601468","https://openalex.org/W2951250252","https://openalex.org/W2963864421","https://openalex.org/W2964067469","https://openalex.org/W2995036248","https://openalex.org/W3194216683","https://openalex.org/W3204272549","https://openalex.org/W6740092555","https://openalex.org/W6741002519","https://openalex.org/W6756303580"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W4252460700","https://openalex.org/W4383268304"],"abstract_inverted_index":{"Curiosity-driven":[0],"reinforcement":[1],"learning":[2],"is":[3],"proposed":[4,141],"to":[5,62,93,123,130,136,177],"solve":[6],"the":[7,58,107,140,157,178],"sparse":[8,164],"extrinsic":[9],"reward":[10],"problem":[11],"by":[12,86,133],"providing":[13],"intrinsic":[14],"rewards":[15],"and":[16,30,97,109],"achieves":[17],"promising":[18],"results.":[19],"However,":[20],"most":[21],"curiosity":[22,59],"algorithms":[23,147],"do":[24],"not":[25],"acquire":[26,124],"sufficient":[27],"states":[28],"knowledge":[29],"can":[31,55],"only":[32],"process":[33],"local":[34],"information,":[35],"which":[36],"would":[37],"suffer":[38],"from":[39],"long":[40],"time":[41],"horizon":[42],"exploration":[43,52,72,112,118],"problem.":[44],"In":[45,66],"this":[46],"paper,":[47],"we":[48,68,114],"propose":[49,115],"a":[50,70,80,88,100,116,171],"curiosity-driven":[51],"strategy":[53],"that":[54,73,120],"continuously":[56],"incentivize":[57],"of":[60,83,103,111,160],"agents":[61,75,99,122],"address":[63],"long-term":[64],"exploration.":[65,104],"particular,":[67],"introduce":[69],"consistent":[71],"provides":[74],"with":[76,143,170],"moderate":[77],"knowledge,":[78],"i.e.,":[79],"certain":[81],"amount":[82],"historical":[84],"information":[85],"maintaining":[87],"finite-length":[89],"state":[90],"feature":[91],"pool":[92],"stimulate":[94],"agent's":[95],"curiosity,":[96],"gives":[98],"novel":[101],"direction":[102],"To":[105],"balance":[106],"consistency":[108],"diversity":[110],"directions,":[113],"high-freedom":[117],"module":[119],"allows":[121],"important":[125],"items,":[126],"such":[127],"as":[128],"keys":[129],"open":[131],"doors,":[132],"adding":[134],"actions":[135],"RND.":[137,181],"We":[138],"compared":[139,176],"method":[142,162],"some":[144],"recent":[145],"advanced":[146],"in":[148,163,167,174],"partial":[149],"Atari":[150],"2600":[151],"games":[152],"environments.":[153],"Experimental":[154],"results":[155],"demonstrate":[156],"superior":[158],"performance":[159],"our":[161],"environments,":[165],"especially":[166],"exploratory":[168],"task":[169],"50%":[172],"improvement":[173],"score":[175],"baseline":[179],"algorithm":[180]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}