{"id":"https://openalex.org/W2508473194","doi":"https://doi.org/10.1109/tii.2016.2602180","title":"Pheromone-Based Planning Strategies in Dyna-Q Learning","display_name":"Pheromone-Based Planning Strategies in Dyna-Q Learning","publication_year":2016,"publication_date":"2016-08-24","ids":{"openalex":"https://openalex.org/W2508473194","doi":"https://doi.org/10.1109/tii.2016.2602180","mag":"2508473194"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2016.2602180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2016.2602180","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Informatics","raw_type":"journal-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/A5061189209","display_name":"Kao\u2010Shing Hwang","orcid":"https://orcid.org/0000-0001-9234-4836"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]},{"id":"https://openalex.org/I152743029","display_name":"Kaohsiung Medical University","ror":"https://ror.org/03gk81f96","country_code":"TW","type":"education","lineage":["https://openalex.org/I152743029"]},{"id":"https://openalex.org/I4210121532","display_name":"Ministry of Health and Welfare","ror":"https://ror.org/024w0ge69","country_code":"TW","type":"government","lineage":["https://openalex.org/I4210121532","https://openalex.org/I4405257903"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kao-Shing Hwang","raw_affiliation_strings":["Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan","Department of Healthcare Administration and Medical Informatic, Kaohsiung Medical University, Kaohsiung, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]},{"raw_affiliation_string":"Department of Healthcare Administration and Medical Informatic, Kaohsiung Medical University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I152743029","https://openalex.org/I4210121532"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001081733","display_name":"Wei\u2010Cheng Jiang","orcid":"https://orcid.org/0000-0003-4432-8801"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Cheng Jiang","raw_affiliation_strings":["Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-4432-8801","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100731680","display_name":"Yu-Jen Chen","orcid":"https://orcid.org/0000-0003-0288-0796"},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Jen Chen","raw_affiliation_strings":["Department of Electrical Engineering, National Chung Cheng University, Chiayi, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chung Cheng University, Chiayi, Taiwan","institution_ids":["https://openalex.org/I148099254"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":3.7795,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.94106772,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"13","issue":"2","first_page":"424","last_page":"435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9925000071525574,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9761999845504761,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7713234424591064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7137041091918945},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.5511826276779175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.542407214641571},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.521480917930603},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5178495049476624},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4125622808933258}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7713234424591064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7137041091918945},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.5511826276779175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.542407214641571},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.521480917930603},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5178495049476624},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4125622808933258},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2016.2602180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2016.2602180","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1557517019","https://openalex.org/W1918371733","https://openalex.org/W1996287559","https://openalex.org/W1997880753","https://openalex.org/W1999912147","https://openalex.org/W2001643966","https://openalex.org/W2050020749","https://openalex.org/W2055654006","https://openalex.org/W2059836092","https://openalex.org/W2077671246","https://openalex.org/W2096001037","https://openalex.org/W2258059573","https://openalex.org/W4214717370","https://openalex.org/W4245108548","https://openalex.org/W6691886369"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915","https://openalex.org/W2089415692"],"abstract_inverted_index":{"A":[0],"Dyna-Q":[1,113,213],"algorithm":[2,114],"is":[3,42,89,102],"known":[4],"as":[5,125],"model-based":[6],"reinforcement":[7],"learning,":[8],"so":[9],"the":[10,17,34,39,46,50,53,96,108,112,117,139,175,180,198,203,212],"learning":[11,88,101,109,209,214],"agent":[12],"not":[13],"only":[14],"interacts":[15],"with":[16,33,184],"environment":[18],"to":[19,44,62,94,98,145,158],"learn":[20],"an":[21,27,74,103,146],"optimal":[22],"policy,":[23],"but":[24],"also":[25],"builds":[26],"environmental":[28,40],"model":[29,41,59,85,97],"simultaneously.":[30],"To":[31,48,106,173],"deal":[32],"shortage":[35],"of":[36,52,111,141,167,179,205],"online":[37],"samples,":[38],"introduced":[43],"achieve":[45,202],"goal.":[47],"enhance":[49],"efficiency":[51,207],"model,":[54,76],"this":[55,83,130],"paper":[56,131],"proposes":[57],"a":[58,126,133,159,185],"shaping":[60,84],"method":[61,136,200],"compensate":[63],"for":[64,149,211],"bleak":[65],"states":[66],"scarcely":[67],"visited":[68],"during":[69],"neighbor":[70],"information.":[71],"After":[72],"acquiring":[73],"accurate":[75],"many":[77],"virtual":[78],"experiences":[79],"are":[80,191],"sampled":[81],"from":[82],"and":[86,170,177,188,208],"indirect":[87,153],"thereby":[90],"performed.":[91],"However,":[92],"how":[93],"use":[95],"speed":[99,110],"up":[100],"important":[104],"issue.":[105],"increase":[107],"based":[115],"on":[116],"prioritized":[118],"sweeping":[119],"that":[120,137,197],"can":[121,201],"actually":[122],"be":[123],"regarded":[124],"breadth-first":[127,171],"search":[128,135],"method,":[129,182],"introduces":[132],"depth-first":[134,168],"applies":[138],"techniques":[140],"ant":[142],"colony":[143],"algorithms":[144],"exploration":[147],"factor":[148],"selecting":[150],"candidates":[151],"in":[152],"learning.":[154],"The":[155,193],"strategy":[156],"evolves":[157],"hybrid":[160],"planning":[161,169],"approach":[162],"by":[163],"proportionally":[164],"interleaving":[165],"executions":[166],"planning.":[172],"verify":[174],"validity":[176],"applicability":[178],"proposed":[181,199],"simulations":[183],"mountain":[186],"car":[187],"maze":[189],"problem":[190],"conducted.":[192],"simulation":[194],"results":[195],"show":[196],"objectives":[204],"sample":[206],"acceleration":[210],"algorithm.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}