{"id":"https://openalex.org/W3106181181","doi":"https://doi.org/10.3233/faia200744","title":"Reward-Free Reinforcement Learning Algorithm Using Prediction Network","display_name":"Reward-Free Reinforcement Learning Algorithm Using Prediction Network","publication_year":2020,"publication_date":"2020-11-09","ids":{"openalex":"https://openalex.org/W3106181181","doi":"https://doi.org/10.3233/faia200744","mag":"3106181181"},"language":"en","primary_location":{"id":"doi:10.3233/faia200744","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200744","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200744","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200744","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052951696","display_name":"Zhen Yu","orcid":"https://orcid.org/0000-0001-7294-7162"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Yu","raw_affiliation_strings":["School of Aerospace Engineering, Xiamen University, Xiamen 361005, China","Shenzhen Research Institute of Xiamen University, Shenzhen 518000, China"],"affiliations":[{"raw_affiliation_string":"School of Aerospace Engineering, Xiamen University, Xiamen 361005, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Shenzhen Research Institute of Xiamen University, Shenzhen 518000, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yimin Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimin Feng","raw_affiliation_strings":["School of Aerospace Engineering, Xiamen University, Xiamen 361005, China"],"affiliations":[{"raw_affiliation_string":"School of Aerospace Engineering, Xiamen University, Xiamen 361005, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100350052","display_name":"Lijun Liu","orcid":"https://orcid.org/0000-0003-4385-8472"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lijun Liu","raw_affiliation_strings":["School of Aerospace Engineering, Xiamen University, Xiamen 361005, China","Shenzhen Research Institute of Xiamen University, Shenzhen 518000, China"],"affiliations":[{"raw_affiliation_string":"School of Aerospace Engineering, Xiamen University, Xiamen 361005, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Shenzhen Research Institute of Xiamen University, Shenzhen 518000, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100350052"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31981305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.7617999911308289,"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"}},"topics":[{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.7617999911308289,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6797000169754028,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.926906943321228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6642800569534302},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6129173636436462},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5639692544937134},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5374062657356262},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5159921646118164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5082318782806396},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4972989857196808},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.488503098487854},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4376063942909241},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.41619613766670227},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38749951124191284},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3692951202392578},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32998204231262207},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2906978726387024},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15294599533081055},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1265650987625122}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.926906943321228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6642800569534302},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6129173636436462},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5639692544937134},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5374062657356262},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5159921646118164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5082318782806396},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4972989857196808},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.488503098487854},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4376063942909241},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.41619613766670227},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38749951124191284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3692951202392578},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32998204231262207},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2906978726387024},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15294599533081055},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1265650987625122},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia200744","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200744","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200744","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia200744","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200744","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200744","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1640859243","display_name":null,"funder_award_id":"9163009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3049186252","display_name":null,"funder_award_id":"2018A03","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3757194791","display_name":null,"funder_award_id":"JCYJ20","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5306782587","display_name":null,"funder_award_id":"202005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6815620850","display_name":null,"funder_award_id":"2018A030313124","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G7977234918","display_name":null,"funder_award_id":"61304110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8591720047","display_name":null,"funder_award_id":"18ZR1443200","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3106181181.pdf","grobid_xml":"https://content.openalex.org/works/W3106181181.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1595483645","https://openalex.org/W2271840356","https://openalex.org/W2337617318","https://openalex.org/W2462906003","https://openalex.org/W2743158846","https://openalex.org/W2883148864","https://openalex.org/W2963864421","https://openalex.org/W2964006217","https://openalex.org/W3011120880","https://openalex.org/W3018779742","https://openalex.org/W4298857966","https://openalex.org/W4394666657","https://openalex.org/W6743505604"],"related_works":["https://openalex.org/W2386410636","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/W2892507673","https://openalex.org/W2025663273"],"abstract_inverted_index":{"In":[0],"general":[1,107],"reinforcement":[2,16,62,158],"learning":[3,63,159],"tasks,":[4],"the":[5,39,60,75,83,88,91,99,103,106,111,118,125,133,139,150,153],"formulation":[6],"of":[7,30,54,105,117,141,152,163],"reward":[8,19,40,44,76,85],"functions":[9,46],"is":[10,21,36,65,71,79,95],"a":[11,27,52,161],"very":[12],"important":[13],"step":[14],"in":[15,26,138,160],"learning.":[17],"The":[18,32,114,147],"function":[20,70],"not":[22],"easy":[23],"to":[24,38,73],"formulate":[25],"large":[28],"number":[29],"systems.":[31,164],"network":[33,93,100,119],"training":[34],"effect":[35],"sensitive":[37],"function,":[41,77],"and":[42,143,155],"different":[43,49],"value":[45,104],"will":[47,120],"get":[48],"results.":[50],"For":[51],"class":[53,162],"systems":[55],"that":[56,98],"meet":[57],"specific":[58],"conditions,":[59],"traditional":[61,84],"method":[64],"improved.":[66],"A":[67],"state":[68,108],"quantity":[69],"designed":[72,96],"replace":[74],"which":[78],"more":[80],"efficient":[81],"than":[82],"function.":[86],"At":[87],"same":[89],"time,":[90],"predictive":[92],"link":[94],"so":[97],"can":[101],"learn":[102],"by":[109],"using":[110],"special":[112],"state.":[113],"overall":[115],"structure":[116],"be":[121],"improved":[122],"based":[123],"on":[124],"Deep":[126],"Deterministic":[127],"Policy":[128],"Gradient":[129],"(DDPG)":[130],"algorithm.":[131],"Finally,":[132],"algorithm":[134,154],"was":[135],"successfully":[136],"applied":[137],"environment":[140],"FrozenLake,":[142],"achieved":[144],"good":[145],"performance.":[146],"experiment":[148],"proves":[149],"effectiveness":[151],"realizes":[156],"rewardless":[157]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}