{"id":"https://openalex.org/W4312560510","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892798","title":"Fast Probabilistic Policy Reuse via Reward Function Fitting","display_name":"Fast Probabilistic Policy Reuse via Reward Function Fitting","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312560510","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892798"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892798","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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 International Joint Conference on Neural Networks (IJCNN)","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/A5101769759","display_name":"Jinmei Liu","orcid":"https://orcid.org/0000-0002-6496-0719"},"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":"Jinmei Liu","raw_affiliation_strings":["Nanjing University,Department of Control and Systems Engineering,Nanjing,China","Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Department of Control and Systems Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376415","display_name":"Zhi Wang","orcid":"https://orcid.org/0000-0003-0304-3965"},"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":"Zhi Wang","raw_affiliation_strings":["Nanjing University,Department of Control and Systems Engineering,Nanjing,China","Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Department of Control and Systems Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697167","display_name":"Chunlin Chen","orcid":"https://orcid.org/0000-0003-3929-4707"},"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":"Chunlin Chen","raw_affiliation_strings":["Nanjing University,Department of Control and Systems Engineering,Nanjing,China","Department of Control and Systems Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Department of Control and Systems Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"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":0.9995999932289124,"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":0.9995999932289124,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9915000200271606,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8451282978057861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7818840742111206},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.7772935628890991},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6957326531410217},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6878945827484131},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6687995195388794},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5635970234870911},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5554291009902954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5371018648147583},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4951848089694977},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4906214773654938},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.44818687438964844},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4411208927631378},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.427839994430542},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4117076098918915},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36958879232406616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1160096526145935},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07659462094306946}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8451282978057861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7818840742111206},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.7772935628890991},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6957326531410217},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6878945827484131},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6687995195388794},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5635970234870911},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5554291009902954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5371018648147583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4951848089694977},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4906214773654938},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.44818687438964844},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4411208927631378},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.427839994430542},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4117076098918915},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36958879232406616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1160096526145935},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07659462094306946},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892798","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W158722652","https://openalex.org/W1481405077","https://openalex.org/W1848094219","https://openalex.org/W2004030284","https://openalex.org/W2031727428","https://openalex.org/W2056584142","https://openalex.org/W2097381042","https://openalex.org/W2110064866","https://openalex.org/W2113953866","https://openalex.org/W2132067420","https://openalex.org/W2133040789","https://openalex.org/W2141559023","https://openalex.org/W2145339207","https://openalex.org/W2151058089","https://openalex.org/W2152414052","https://openalex.org/W2153232138","https://openalex.org/W2153353285","https://openalex.org/W2158782408","https://openalex.org/W2165698076","https://openalex.org/W2342662072","https://openalex.org/W2440926996","https://openalex.org/W2464736835","https://openalex.org/W2605369401","https://openalex.org/W2754517384","https://openalex.org/W2760355785","https://openalex.org/W2766447205","https://openalex.org/W2787938642","https://openalex.org/W2911087563","https://openalex.org/W2949600457","https://openalex.org/W2952465248","https://openalex.org/W2965407115","https://openalex.org/W2977481643","https://openalex.org/W2982316857","https://openalex.org/W2999912861","https://openalex.org/W3093037198","https://openalex.org/W3113170268","https://openalex.org/W3117812535","https://openalex.org/W3168994162","https://openalex.org/W4214717370","https://openalex.org/W4287073210","https://openalex.org/W4287689437","https://openalex.org/W4298174377","https://openalex.org/W6628767384","https://openalex.org/W6638853687","https://openalex.org/W6674600207","https://openalex.org/W6676875888","https://openalex.org/W6676927033","https://openalex.org/W6679818365","https://openalex.org/W6680962669","https://openalex.org/W6681686657","https://openalex.org/W6682185026","https://openalex.org/W6685726866","https://openalex.org/W6698463750","https://openalex.org/W6704571135","https://openalex.org/W6718190810","https://openalex.org/W6719360576","https://openalex.org/W6736469832","https://openalex.org/W6748839928","https://openalex.org/W6768511085","https://openalex.org/W6780559895","https://openalex.org/W6782022165","https://openalex.org/W6784646362","https://openalex.org/W6796505199"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"Transfer":[0],"learning":[1,9,39,73],"has":[2,19],"shown":[3],"great":[4],"potential":[5],"to":[6,63,82,94,111,133,156],"accelerate":[7],"reinforcement":[8,72],"(RL)":[10],"by":[11,45],"utilizing":[12],"prior":[13],"knowledge":[14],"of":[15,41,130,176,178],"relevant":[16],"task":[17,44],"that":[18,90,189],"been":[20],"learned":[21],"in":[22,70,181,198],"the":[23,38,42,51,78,108,113,128,147,153,157,168],"past.":[24],"Policy":[25],"Reuse":[26],"Q-learning":[27],"(PRQL)":[28],"is":[29,136],"a":[30,85,104,141],"general":[31],"policy":[32,52,68,87,161,196],"transfer":[33,197],"framework,":[34],"which":[35,135,150],"speeds":[36],"up":[37],"process":[40],"target":[43],"probabilistically":[46],"reusing":[47],"source":[48],"policies":[49],"from":[50],"library.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,76,139],"propose":[58,140],"an":[59,131],"improved":[60],"PRQL":[61,80,100],"method":[62,180,191],"achieve":[64,194],"more":[65,96,162],"fast":[66],"probabilistic":[67],"reuse":[69,88,160],"deep":[71],"(DRL).":[74],"First,":[75],"extend":[77],"basic":[79],"algorithm":[81,89],"DRL,":[83],"proposing":[84],"probability":[86],"builds":[91],"on":[92,107,145],"DRL":[93],"solve":[95],"complex":[97,183],"problems.":[98],"Second,":[99],"algorithms":[101],"usually":[102],"use":[103],"metric":[105,143],"based":[106,144],"average":[109],"gain":[110],"measure":[112],"similarity":[114],"between":[115],"tasks.":[116,185,200],"However,":[117],"it":[118],"contains":[119],"very":[120],"limited":[121],"information":[122],"and":[123,164,174],"must":[124],"be":[125],"delayed":[126],"until":[127],"end":[129],"episode":[132],"update,":[134],"inefficient.":[137],"Instead,":[138],"new":[142],"fitting":[146],"reward":[148],"function,":[149],"can":[151,192],"make":[152],"agent":[154],"converge":[155],"most":[158],"suitable":[159],"quickly":[163],"accurately.":[165],"We":[166],"demonstrate":[167],"detection":[169],"accuracy,":[170],"received":[171],"cumulative":[172],"reward,":[173],"speed":[175],"convergence":[177],"our":[179,190],"three":[182],"Markov":[184],"Experimental":[186],"results":[187],"show":[188],"consistently":[193],"efficient":[195],"these":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}