{"id":"https://openalex.org/W2605371229","doi":"https://doi.org/10.3233/978-1-61499-522-7-200","title":"An Improved Dyna-Q Algorithm Based in Reverse Model Learning","display_name":"An Improved Dyna-Q Algorithm Based in Reverse Model Learning","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2605371229","doi":"https://doi.org/10.3233/978-1-61499-522-7-200","mag":"2605371229"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-522-7-200","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-522-7-200","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031420561","display_name":"Tseng Yi-Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tseng Yi-Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061189209","display_name":"Kao\u2010Shing Hwang","orcid":"https://orcid.org/0000-0001-9234-4836"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hwang Kao-Shing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032732866","display_name":"Weicheng Jiang","orcid":"https://orcid.org/0000-0003-2939-2231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang Wei-Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102134214","display_name":"Tsung-Chuan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang Tsung-Chuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5116359731","display_name":"Chen Song-Shyong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Song-Shyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41251624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.6592000126838684,"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.6592000126838684,"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/T14225","display_name":"Advanced Sensor and Control Systems","score":0.5885999798774719,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5651478171348572},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4675074517726898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34920042753219604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5651478171348572},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4675074517726898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34920042753219604}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/978-1-61499-522-7-200","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-522-7-200","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Q-Learning":[0],"is":[1,65],"one":[2],"of":[3,118],"the":[4,21,53,57,79,94,98,107,115],"well-known":[5],"model-free":[6],"RL":[7],"methods.":[8,109],"When":[9],"it":[10,15,68],"discovers":[11],"a":[12],"good":[13],"reward,":[14],"needs":[16],"much":[17],"iteration":[18],"to":[19,37,46,55,84,92,105],"diffuse":[20],"information.":[22],"In":[23,82],"this":[24,86],"paper,":[25],"we":[26,88,101],"used":[27],"an":[28],"adaptive":[29],"model":[30,64],"learning":[31,80],"method":[32,120],"based":[33],"on":[34],"tree":[35],"structure":[36],"imitate":[38,56],"experience.":[39],"Predictions":[40],"let":[41],"agent":[42],"have":[43],"extra":[44],"experience":[45],"learn":[47],"policy":[48],"indirectly.":[49],"Agent":[50],"can":[51,121],"use":[52],"tree-model":[54],"transition":[58],"between":[59],"two":[60,90,103],"states.":[61,73],"However,":[62],"when":[63],"not":[66],"accurate,":[67],"may":[69],"get":[70],"through":[71,75],"absorbing":[72,76],"Getting":[74],"states":[77],"influence":[78],"efficiency.":[81],"order":[83],"solve":[85],"problem,":[87],"propose":[89],"methods":[91],"enhance":[93],"tree-model.":[95],"For":[96],"demonstrating":[97],"proposed":[99,108],"method,":[100],"introduce":[102],"simulations":[104],"verify":[106],"The":[110],"simulation":[111],"results":[112],"demonstrate":[113],"that":[114],"training":[116],"rate":[117],"our":[119],"improve":[122],"obviously.":[123]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}