{"id":"https://openalex.org/W4399055968","doi":"https://doi.org/10.1007/s11063-024-11632-x","title":"Hierarchical Reinforcement Learning from Demonstration via Reachability-Based Reward Shaping","display_name":"Hierarchical Reinforcement Learning from Demonstration via Reachability-Based Reward Shaping","publication_year":2024,"publication_date":"2024-05-27","ids":{"openalex":"https://openalex.org/W4399055968","doi":"https://doi.org/10.1007/s11063-024-11632-x"},"language":"en","primary_location":{"id":"doi:10.1007/s11063-024-11632-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11632-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11632-x.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11632-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007495956","display_name":"Xiaozhu Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaozhu Gao","raw_affiliation_strings":["Guangzhou Institute of Technology, Xidian University, Guangzhou, 510555, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou Institute of Technology, Xidian University, Guangzhou, 510555, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100766359","display_name":"Jinhui Liu","orcid":"https://orcid.org/0000-0001-8032-5099"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I4210128676","display_name":"Human Computer Interaction (Switzerland)","ror":"https://ror.org/036dv6j71","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210128676"]}],"countries":["CH","CN"],"is_corresponding":true,"raw_author_name":"Jinhui Liu","raw_affiliation_strings":["Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi, Xi\u2019an, 710071, China","School of Computer Science and Technology, Xidian University, Xi\u2019an, 710071, China","School of Computer Science and Technology, Xidian University, Xi'an, 710071, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi, Xi\u2019an, 710071, China","institution_ids":["https://openalex.org/I4210128676"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi\u2019an, 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi'an, 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083468959","display_name":"Bo Wan","orcid":"https://orcid.org/0000-0002-3410-9560"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I4210128676","display_name":"Human Computer Interaction (Switzerland)","ror":"https://ror.org/036dv6j71","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210128676"]}],"countries":["CH","CN"],"is_corresponding":false,"raw_author_name":"Bo Wan","raw_affiliation_strings":["Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi, Xi\u2019an, 710071, China","School of Computer Science and Technology, Xidian University, Xi\u2019an, 710071, China","School of Computer Science and Technology, Xidian University, Xi'an, 710071, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi, Xi\u2019an, 710071, China","institution_ids":["https://openalex.org/I4210128676"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi\u2019an, 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi'an, 710071, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102970747","display_name":"Lingling An","orcid":"https://orcid.org/0000-0002-0103-489X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingling An","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi\u2019an, 710071, China","School of Computer Science and Technology, Xidian University, Xi'an, 710071, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi\u2019an, 710071, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi'an, 710071, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100766359"],"corresponding_institution_ids":["https://openalex.org/I149594827","https://openalex.org/I4210128676"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":3.0387,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92207315,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"56","issue":"3","first_page":null,"last_page":null},"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.987500011920929,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9007194638252258},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.877700686454773},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7467937469482422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5988343954086304},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5734943747520447},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5032238364219666},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41847363114356995},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12045800685882568}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9007194638252258},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.877700686454773},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7467937469482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5988343954086304},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5734943747520447},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5032238364219666},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41847363114356995},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12045800685882568},{"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:10.1007/s11063-024-11632-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11632-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11632-x.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11063-024-11632-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11632-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11632-x.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399055968.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1592847719","https://openalex.org/W1981276685","https://openalex.org/W2158782408","https://openalex.org/W2573393487","https://openalex.org/W2749604329","https://openalex.org/W2754517384","https://openalex.org/W2788862220","https://openalex.org/W2883140436","https://openalex.org/W2887039782","https://openalex.org/W2891655128","https://openalex.org/W2910988768","https://openalex.org/W2963099939","https://openalex.org/W3041838758","https://openalex.org/W3090027660","https://openalex.org/W3094075584","https://openalex.org/W3123212791","https://openalex.org/W3128707967","https://openalex.org/W3132357549","https://openalex.org/W3134939669","https://openalex.org/W3136456184","https://openalex.org/W3168892396","https://openalex.org/W3206820790","https://openalex.org/W3208890675","https://openalex.org/W4225165449","https://openalex.org/W4229060449","https://openalex.org/W4304142069","https://openalex.org/W4307927178","https://openalex.org/W4309344387","https://openalex.org/W4382318696"],"related_works":["https://openalex.org/W2127267268","https://openalex.org/W2136512912","https://openalex.org/W2067910792","https://openalex.org/W2156446763","https://openalex.org/W2150194458","https://openalex.org/W2143461633","https://openalex.org/W4321471459","https://openalex.org/W2889071233","https://openalex.org/W2380814829","https://openalex.org/W2387511021"],"abstract_inverted_index":{"Abstract":[0],"Hierarchical":[1],"reinforcement":[2,41],"learning":[3,42,118,130],"(HRL)":[4],"has":[5],"achieved":[6],"remarkable":[7],"success":[8],"and":[9,14,26,154],"significant":[10],"progress":[11],"in":[12],"complex":[13,151],"long-term":[15],"decision-making":[16],"problems.":[17],"However,":[18],"HRL":[19,98],"training":[20,52],"typically":[21],"entails":[22],"substantial":[23],"computational":[24],"costs":[25],"an":[27],"enormous":[28],"number":[29],"of":[30,54,58,65,93,120,126,139],"samples.":[31],"One":[32],"effective":[33],"approach":[34],"to":[35,49,88,115],"tackle":[36],"this":[37,77,79,127],"challenge":[38],"is":[39,60,107],"hierarchical":[40],"from":[43],"demonstrations":[44,48,70,95],"(HRLfD),":[45],"which":[46,110],"leverages":[47],"expedite":[50],"the":[51,63,66,90,97,112,117,124,129,137,140,145,155],"process":[53],"HRL.":[55],"The":[56,100],"effectiveness":[57],"HRLfD":[59,102,165],"contingent":[61],"upon":[62],"quality":[64],"demonstrations;":[67],"hence,":[68],"suboptimal":[69,94,141],"may":[71],"impede":[72],"efficient":[73],"learning.":[74],"To":[75],"address":[76],"issue,":[78],"paper":[80],"proposes":[81],"a":[82],"reachability-based":[83],"reward":[84],"shaping":[85],"(RbRS)":[86],"method":[87,114,161],"alleviate":[89],"negative":[91],"interference":[92],"for":[96],"agent.":[99],"novel":[101],"algorithm":[103,148],"based":[104],"on":[105,149],"RbRS":[106,113],"named":[108],"HRLfD-RbRS,":[109],"incorporates":[111],"enhance":[116],"efficiency":[119],"HRLfD.":[121],"Moreover,":[122],"with":[123],"help":[125],"method,":[128],"agent":[131],"can":[132],"explore":[133],"better":[134],"policies":[135],"under":[136],"guidance":[138],"demonstration.":[142],"We":[143],"evaluate":[144],"proposed":[146],"HRLfD-RbRS":[147],"various":[150],"robotic":[152],"tasks,":[153],"experimental":[156],"results":[157],"demonstrate":[158],"that":[159],"our":[160],"outperforms":[162],"current":[163],"state-of-the-art":[164],"algorithms.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}