{"id":"https://openalex.org/W4317514661","doi":"https://doi.org/10.1109/ccis57298.2022.10016361","title":"SNSE: State Novelty Sampling Exploration","display_name":"SNSE: State Novelty Sampling Exploration","publication_year":2022,"publication_date":"2022-11-26","ids":{"openalex":"https://openalex.org/W4317514661","doi":"https://doi.org/10.1109/ccis57298.2022.10016361"},"language":"en","primary_location":{"id":"doi:10.1109/ccis57298.2022.10016361","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ccis57298.2022.10016361","pdf_url":null,"source":{"id":"https://openalex.org/S4363608348","display_name":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100345005","display_name":"Shaojie Li","orcid":"https://orcid.org/0000-0001-6460-4557"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojie Li","raw_affiliation_strings":["Shanghai University,Shanghai,China,200444"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai,China,200444","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426947","display_name":"Xiangfeng Luo","orcid":"https://orcid.org/0000-0003-4577-9241"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangfeng Luo","raw_affiliation_strings":["Shanghai University,Shanghai,China,200444"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai,China,200444","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101902939","display_name":"Zhenyu Zhang","orcid":"https://orcid.org/0000-0002-9470-7132"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhang","raw_affiliation_strings":["Shanghai University,Shanghai,China,200444"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai,China,200444","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101534224","display_name":"Hang Yu","orcid":"https://orcid.org/0009-0005-0100-7989"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Yu","raw_affiliation_strings":["Shanghai University,Shanghai,China,200444"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai,China,200444","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086702173","display_name":"Shaorong Xie","orcid":"https://orcid.org/0000-0002-8016-9310"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaorong Xie","raw_affiliation_strings":["Shanghai University,Shanghai,China,200444"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai,China,200444","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19356148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"173","last_page":"180"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9840999841690063,"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"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9804999828338623,"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/novelty","display_name":"Novelty","score":0.9042221307754517},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7492055296897888},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7094661593437195},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6195618510246277},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6034033894538879},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5479186177253723},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48924899101257324},{"id":"https://openalex.org/keywords/intrinsic-motivation","display_name":"Intrinsic motivation","score":0.47016641497612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40567106008529663},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1609736979007721},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1102035641670227},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09523186087608337},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09028390049934387}],"concepts":[{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.9042221307754517},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7492055296897888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7094661593437195},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6195618510246277},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6034033894538879},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5479186177253723},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48924899101257324},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.47016641497612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40567106008529663},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1609736979007721},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1102035641670227},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09523186087608337},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09028390049934387},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccis57298.2022.10016361","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ccis57298.2022.10016361","pdf_url":null,"source":{"id":"https://openalex.org/S4363608348","display_name":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2168405694","https://openalex.org/W2596982695","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2787938642","https://openalex.org/W2895453875","https://openalex.org/W2902298341","https://openalex.org/W2904246096","https://openalex.org/W2907923173","https://openalex.org/W2914261249","https://openalex.org/W2922388521","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2964067469","https://openalex.org/W2965050397","https://openalex.org/W2965435131","https://openalex.org/W2969456553","https://openalex.org/W2994943647","https://openalex.org/W2997289589","https://openalex.org/W2999714443","https://openalex.org/W3034769194","https://openalex.org/W3119264617","https://openalex.org/W3134847873","https://openalex.org/W3172543069","https://openalex.org/W3184813433","https://openalex.org/W4220747123","https://openalex.org/W4287071861","https://openalex.org/W4287867830","https://openalex.org/W4288266427","https://openalex.org/W4294982428","https://openalex.org/W6717230150","https://openalex.org/W6735033012","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6754957883","https://openalex.org/W6756303580","https://openalex.org/W6757058172","https://openalex.org/W6757592117","https://openalex.org/W6758978475","https://openalex.org/W6760518690","https://openalex.org/W6766694020","https://openalex.org/W6771101658","https://openalex.org/W6771807793"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W3126131230","https://openalex.org/W2347541121","https://openalex.org/W4288804799","https://openalex.org/W2080951048","https://openalex.org/W3032237421","https://openalex.org/W2390346111","https://openalex.org/W3011883280","https://openalex.org/W2369082698","https://openalex.org/W2401808953"],"abstract_inverted_index":{"Exploration":[0,117],"in":[1],"sparse":[2,19,163],"reward":[3,21,103],"reinforcement":[4],"learning":[5],"remains":[6],"an":[7],"open":[8],"challenge.":[9],"Many":[10],"state-of-the-art":[11],"methods":[12],"use":[13],"intrinsic":[14,40,46,69,105,122,136],"motivation":[15],"to":[16,28,64,78,142,158],"complement":[17],"the":[18,24,58,62,66,76,108,121,128,140,147,173,181,185,194],"extrinsic":[20,43,53,71,102,124,160],"signal,":[22],"giving":[23],"agent":[25,77,141],"more":[26],"opportunities":[27],"receive":[29],"feedback":[30],"during":[31,146],"exploration.":[32],"Commonly":[33],"these":[34],"signals":[35],"are":[36,48],"summed":[37],"directly":[38,51,138],"as":[39],"rewards":[41,47,55,137,164],"and":[42,56,70,95,104,123,150,179,199],"rewards.":[44,72,161],"However":[45],"non-stationary,":[49],"which":[50],"contaminates":[52],"environmental":[54],"changes":[57],"optimization":[59,154,197],"objective":[60],"of":[61,68,175,184],"policy":[63,81,153,195],"maximize":[65,159],"sum":[67],"This":[73,91],"could":[74],"lead":[75],"a":[79,93],"mixture":[80],"that":[82,127,151,169],"neither":[83],"conducts":[84],"exploration":[85,148],"nor":[86],"task":[87],"score":[88],"fulfillment":[89],"resolutely.":[90],"adopts":[92],"simple":[94],"generic":[96],"perspective,":[97],"where":[98],"we":[99],"explicitly":[100],"disentangle":[101],"reward.":[106],"Through":[107],"multiple":[109],"sampling":[110],"mechanism,":[111],"our":[112,152,166],"method,":[113],"State":[114],"Novelty":[115],"Sampling":[116],"(SNSE),":[118],"cleverly":[119],"decouples":[120],"rewards,":[125,189],"so":[126],"two":[129],"can":[130,171],"take":[131],"their":[132],"respective":[133],"roles.":[134],"Letting":[135],"guide":[139],"explore":[143],"novel":[144],"samples":[145],"phase,":[149],"goal":[155],"is":[156],"still":[157],"In":[162],"environments,":[165],"experiments":[167],"show":[168],"SNSE":[170,190],"improve":[172,180],"efficiency":[174],"exploring":[176],"unknown":[177],"states":[178],"final":[182],"performance":[183,201],"policy.":[186],"Under":[187],"dense":[188],"do":[191],"not":[192],"make":[193],"produce":[196],"bias":[198],"cause":[200],"loss.":[202]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}