{"id":"https://openalex.org/W4313887415","doi":"https://doi.org/10.1109/taslp.2023.3235202","title":"Hierarchical Reinforcement Learning With Guidance for Multi-Domain Dialogue Policy","display_name":"Hierarchical Reinforcement Learning With Guidance for Multi-Domain Dialogue Policy","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4313887415","doi":"https://doi.org/10.1109/taslp.2023.3235202"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3235202","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3235202","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10011569.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10011569.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043243811","display_name":"Mahdin Rohmatillah","orcid":"https://orcid.org/0000-0001-8417-2165"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Mahdin Rohmatillah","raw_affiliation_strings":["EECS International Graduate Program, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-8417-2165","affiliations":[{"raw_affiliation_string":"EECS International Graduate Program, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-3466-8941","affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":2.6966,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91290765,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"748","last_page":"761"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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":0.8718643188476562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7842077016830444},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6642060279846191},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.635514497756958},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6225588321685791},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.591442346572876},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5773611068725586},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5327926278114319},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5169105529785156},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4987301826477051},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.48031777143478394},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.42674335837364197},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42398688197135925},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3338702321052551}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8718643188476562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842077016830444},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6642060279846191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.635514497756958},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6225588321685791},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.591442346572876},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5773611068725586},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5327926278114319},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5169105529785156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4987301826477051},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.48031777143478394},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.42674335837364197},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42398688197135925},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3338702321052551},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3235202","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3235202","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10011569.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2023.3235202","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3235202","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10011569.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.47999998927116394}],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313887415.pdf","grobid_xml":"https://content.openalex.org/works/W4313887415.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W2119717200","https://openalex.org/W2156517809","https://openalex.org/W2169203263","https://openalex.org/W2187089797","https://openalex.org/W2605982830","https://openalex.org/W2736601468","https://openalex.org/W2739936944","https://openalex.org/W2798494119","https://openalex.org/W2798914047","https://openalex.org/W2806600904","https://openalex.org/W2889448364","https://openalex.org/W2896457183","https://openalex.org/W2915295540","https://openalex.org/W2953071719","https://openalex.org/W2954492830","https://openalex.org/W2963412005","https://openalex.org/W2963433587","https://openalex.org/W2963508354","https://openalex.org/W2963797754","https://openalex.org/W2964006684","https://openalex.org/W2964180249","https://openalex.org/W2970828515","https://openalex.org/W2978017171","https://openalex.org/W2985067290","https://openalex.org/W2988647680","https://openalex.org/W2997108628","https://openalex.org/W2997771882","https://openalex.org/W3009593063","https://openalex.org/W3034782127","https://openalex.org/W3037879762","https://openalex.org/W3046799624","https://openalex.org/W3095200696","https://openalex.org/W3099140719","https://openalex.org/W3100128199","https://openalex.org/W3105184920","https://openalex.org/W3114038149","https://openalex.org/W3117383065","https://openalex.org/W3126860450","https://openalex.org/W3128625458","https://openalex.org/W3161450564","https://openalex.org/W3197004354","https://openalex.org/W3208178363","https://openalex.org/W4210790685","https://openalex.org/W4225322339","https://openalex.org/W4255900881","https://openalex.org/W4294974598","https://openalex.org/W4295249402","https://openalex.org/W4312554247","https://openalex.org/W4385245566","https://openalex.org/W4389009381","https://openalex.org/W6627932998","https://openalex.org/W6712785310","https://openalex.org/W6741002519","https://openalex.org/W6745347688","https://openalex.org/W6752089545","https://openalex.org/W6764961350","https://openalex.org/W6768851824","https://openalex.org/W6780159193","https://openalex.org/W6784915420","https://openalex.org/W6790670656","https://openalex.org/W6796289742","https://openalex.org/W6874449412"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2782058284","https://openalex.org/W3103937890"],"abstract_inverted_index":{"Achieving":[0],"high":[1,101],"performance":[2,102,190],"in":[3,47,121,175,191,201],"a":[4,29,136],"multi-domain":[5,68],"dialogue":[6,49,61,106,137,147,192],"system":[7,50,203],"with":[8,75,95,111,138,171],"low":[9],"computation":[10],"is":[11,39,114,129],"undoubtedly":[12],"challenging.":[13],"Previous":[14],"works":[15],"applying":[16],"an":[17,81,104],"end-to-end":[18,202],"approach":[19],"have":[20],"been":[21],"very":[22],"successful.":[23],"However,":[24],"the":[25,33,42,48,58,65,86,90,118,126,139,152,165,169,172,176,185,197],"computational":[26],"cost":[27],"remains":[28],"major":[30],"issue":[31],"since":[32],"large-sized":[34],"language":[35],"model":[36],"using":[37],"GPT-2":[38,198],"required.":[40],"Meanwhile,":[41],"optimization":[43,194],"for":[44,57],"individual":[45],"components":[46],"has":[51],"not":[52],"shown":[53],"promising":[54],"result,":[55],"especially":[56],"component":[59],"of":[60,67,135],"management":[62],"due":[63],"to":[64,99,116,131,144],"complexity":[66],"state":[69],"and":[70,89,159,195],"action":[71,157,160],"representation.":[72,123],"To":[73],"cope":[74],"these":[76],"issues,":[77],"this":[78],"article":[79],"presents":[80],"efficient":[82,146],"guidance":[83,153],"learning":[84,88,93,149],"where":[85],"imitation":[87],"hierarchical":[91],"reinforcement":[92],"(HRL)":[94],"human-in-the-loop":[96],"are":[97],"performed":[98],"achieve":[100],"via":[103],"inexpensive":[105],"agent.":[107],"The":[108],"behavior":[109],"cloning":[110],"auxiliary":[112],"tasks":[113],"exploited":[115],"identify":[117],"important":[119],"features":[120],"latent":[122],"In":[124],"particular,":[125],"proposed":[127,186],"HRL":[128],"designed":[130],"treat":[132],"each":[133],"goal":[134],"corresponding":[140],"sub-policy":[141],"so":[142],"as":[143,162,164],"provide":[145],"policy":[148,193],"by":[150],"utilizing":[151],"from":[154,168],"human":[155],"through":[156],"pruning":[158],"evaluation,":[161],"well":[163],"reward":[166],"obtained":[167],"interaction":[170],"simulated":[173],"user":[174],"environment.":[177],"Experimental":[178],"results":[179],"on":[180],"ConvLab-2":[181],"framework":[182],"show":[183],"that":[184],"method":[187],"achieves":[188],"state-of-the-art":[189],"outperforms":[196],"based":[199],"solutions":[200],"evaluation.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}