{"id":"https://openalex.org/W4319663730","doi":"https://doi.org/10.1109/tmm.2023.3243618","title":"Skill-Based Hierarchical Reinforcement Learning for Target Visual Navigation","display_name":"Skill-Based Hierarchical Reinforcement Learning for Target Visual Navigation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4319663730","doi":"https://doi.org/10.1109/tmm.2023.3243618"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3243618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3243618","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5051448188","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0001-6599-3638"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106746235","display_name":"Zhihao Wu","orcid":"https://orcid.org/0000-0003-1118-5146"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Wu","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000221151","display_name":"Xiaobo Hu","orcid":"https://orcid.org/0000-0001-6541-2784"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Hu","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102790320","display_name":"Youfang Lin","orcid":"https://orcid.org/0000-0002-1611-4323"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youfang Lin","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026666435","display_name":"Kai Lv","orcid":"https://orcid.org/0000-0001-6533-5176"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Lv","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051448188"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":4.3045,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.95662951,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"8920","last_page":"8932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.992900013923645,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.992900013923645,"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"}},{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12546","display_name":"Smart Parking Systems Research","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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":0.8030915856361389},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7801610827445984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6122199892997742},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5839739441871643},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5694313645362854},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5106661915779114},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3447428345680237},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.337371289730072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8030915856361389},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7801610827445984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122199892997742},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5839739441871643},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5694313645362854},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5106661915779114},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3447428345680237},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.337371289730072},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3243618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3243618","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G3261543426","display_name":null,"funder_award_id":"62206013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4144150693","display_name":null,"funder_award_id":"2022M720391","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G8689330525","display_name":null,"funder_award_id":"L211016","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2006501475","https://openalex.org/W2095784398","https://openalex.org/W2108598243","https://openalex.org/W2109910161","https://openalex.org/W2143824592","https://openalex.org/W2143864104","https://openalex.org/W2194775991","https://openalex.org/W2621003976","https://openalex.org/W2962732398","https://openalex.org/W2962887844","https://openalex.org/W2963142324","https://openalex.org/W2963800628","https://openalex.org/W2967853831","https://openalex.org/W3023254696","https://openalex.org/W3034475678","https://openalex.org/W3034549794","https://openalex.org/W3096345170","https://openalex.org/W3096609285","https://openalex.org/W3100100339","https://openalex.org/W3109001458","https://openalex.org/W3173993018","https://openalex.org/W3179552988","https://openalex.org/W3206064582","https://openalex.org/W3207872317","https://openalex.org/W4214643368","https://openalex.org/W6627932998","https://openalex.org/W6629438869","https://openalex.org/W6692846177","https://openalex.org/W6703271639","https://openalex.org/W6734215269","https://openalex.org/W6739901393","https://openalex.org/W6747106673","https://openalex.org/W6748603076","https://openalex.org/W6754725917","https://openalex.org/W6756121852","https://openalex.org/W6764724164","https://openalex.org/W6767317771","https://openalex.org/W6780443396","https://openalex.org/W6790124654","https://openalex.org/W6791136821"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W3196817267"],"abstract_inverted_index":{"Target":[0],"visual":[1,17,36,84],"navigation":[2,37,67],"aims":[3],"at":[4,107],"controlling":[5],"the":[6,27,43,46,52,61,99,146,161,168,174,195],"agent":[7,28,47],"to":[8,29,31,114,141,145,153,193],"find":[9],"a":[10,15,39,74,88,180],"target":[11,35,83],"object":[12],"based":[13],"on":[14,59,155],"monocular":[16],"RGB":[18],"image":[19],"in":[20,167,183],"each":[21,108],"step.":[22,109],"It":[23],"is":[24,38,48,151],"crucial":[25],"for":[26,50,54,82],"adapt":[30],"new":[32],"environments.":[33,186],"As":[34],"complex":[40],"task,":[41],"understanding":[42],"behavior":[44],"of":[45,66,163,197],"beneficial":[49],"analyzing":[51],"reasons":[53],"failure.":[55],"This":[56],"work":[57],"focuses":[58],"improving":[60],"readability":[62],"and":[63,91,125,137],"success":[64],"rate":[65],"policies.":[68],"In":[69,130],"this":[70],"paper,":[71],"we":[72,132,188],"propose":[73,133],"framework":[75],"named":[76],"Skill-based":[77],"Hierarchical":[78],"Reinforcement":[79],"Learning":[80],"(SHRL)":[81],"navigation.":[85,164],"SHRL":[86],"contains":[87],"high-level":[89,96,147],"policy":[90,97],"three":[92,117],"low-level":[93,105,157],"skills.":[94],"The":[95],"accomplishes":[98],"task":[100],"by":[101,179],"utilizing":[102],"or":[103],"stopping":[104],"skills":[106,111,158],"Low-level":[110],"are":[112],"designed":[113,152],"separately":[115],"solve":[116],"sub-tasks,":[118],"i.e.,":[119],"<italic":[120,126],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[121,127],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Search,":[122],"Adjustment</i>":[123],",":[124],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Exploration</i>":[128],".":[129],"addition,":[131],"an":[134],"Abstract":[135,149],"Representation":[136,150],"two":[138],"penalty":[139],"items":[140],"feed":[142],"robust":[143],"features":[144],"policy.":[148],"focus":[154],"selecting":[156],"rather":[159],"than":[160],"details":[162],"Experimental":[165],"results":[166],"artificial":[169],"environment":[170],"AI2-Thor":[171],"indicate":[172],"that":[173],"proposed":[175],"method":[176],"outperforms":[177],"state-of-the-art":[178],"large":[181],"margin":[182],"unseen":[184],"indoor":[185],"Moreover,":[187],"also":[189],"provide":[190],"case":[191],"studies":[192],"illustrate":[194],"advantages":[196],"SHRL.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}