{"id":"https://openalex.org/W4415428256","doi":"https://doi.org/10.3233/faia251090","title":"Skill-Enhanced Reinforcement Learning Acceleration from Heterogeneous Demonstrations","display_name":"Skill-Enhanced Reinforcement Learning Acceleration from Heterogeneous Demonstrations","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428256","doi":"https://doi.org/10.3233/faia251090"},"language":null,"primary_location":{"id":"doi:10.3233/faia251090","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251090","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251090","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115592902","display_name":"Hanping Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Hanping Zhang","raw_affiliation_strings":["School of Computer Science, Carleton University, Ottawa, Canada, jagzhang@cmail.carleton.ca, yuhong.guo@carleton.ca"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carleton University, Ottawa, Canada, jagzhang@cmail.carleton.ca, yuhong.guo@carleton.ca","institution_ids":["https://openalex.org/I67031392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102254246","display_name":"Yuhong Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]},{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuhong Guo","raw_affiliation_strings":["Canada CIFAR AI Chair, Amii, Canada","School of Computer Science, Carleton University, Ottawa, Canada, jagzhang@cmail.carleton.ca, yuhong.guo@carleton.ca"],"affiliations":[{"raw_affiliation_string":"Canada CIFAR AI Chair, Amii, Canada","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"School of Computer Science, Carleton University, Ottawa, Canada, jagzhang@cmail.carleton.ca, yuhong.guo@carleton.ca","institution_ids":["https://openalex.org/I67031392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5115592902"],"corresponding_institution_ids":["https://openalex.org/I67031392"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50536181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9898999929428101,"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":0.9898999929428101,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9132000207901001,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9046000242233276,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8903999924659729},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.718999981880188},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5274999737739563},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.3912999927997589},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.364300012588501},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.35679998993873596},{"id":"https://openalex.org/keywords/online-machine-learning","display_name":"Online machine learning","score":0.3506999909877777},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3199999928474426}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8903999924659729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764000296592712},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.718999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.567300021648407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5476999878883362},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3912999927997589},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.35679998993873596},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.3506999909877777},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.31700000166893005},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.30550000071525574},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.2578999996185303},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251090","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251090","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251090","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251090","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning":[0,10,59],"from":[1,79],"Demonstration":[2],"(LfD)":[3],"is":[4],"a":[5,51,64,98,112,126],"well-established":[6],"problem":[7],"in":[8,87,116,159,167],"Reinforcement":[9,58],"(RL),":[11],"which":[12],"aims":[13],"to":[14,22,39,103,132],"facilitate":[15],"rapid":[16],"RL":[17,25,43,120,151],"by":[18,77],"leveraging":[19],"expert":[20,32,81],"demonstrations":[21,82,86],"pre-train":[23],"the":[24,28,88,105,117,168],"agent.":[26],"However,":[27],"limited":[29],"availability":[30],"of":[31,111],"demonstration":[33],"data":[34,129,134],"often":[35],"hinders":[36],"its":[37],"ability":[38],"effectively":[40],"aid":[41],"downstream":[42,118,164],"learning.":[44],"To":[45],"address":[46],"this":[47],"problem,":[48],"we":[49,124],"propose":[50,125],"novel":[52],"two-stage":[53],"method":[54],"dubbed":[55],"as":[56],"Skill-enhanced":[57],"Acceleration":[60],"(SeRLA).":[61],"SeRLA":[62,155],"introduces":[63],"skill-level":[65,128],"adversarial":[66],"Positive-Unlabeled":[67],"(PU)":[68],"learning":[69,78,91,142,162],"model":[70],"that":[71,154],"extracts":[72],"useful":[73],"skill":[74,113,140,144],"prior":[75,90,141],"knowledge":[76],"both":[80,139],"and":[83,136,143],"general":[84],"low-cost":[85],"offline":[89],"stage.":[92,121],"Building":[93],"on":[94,163],"this,":[95],"it":[96],"employs":[97],"skill-based":[99],"soft":[100],"actor-critic":[101],"algorithm":[102],"leverage":[104],"acquired":[106],"priors":[107],"for":[108],"efficient":[109],"training":[110,170],"policy":[114,145],"network":[115],"online":[119],"In":[122],"addition,":[123],"simple":[127],"enhancement":[130],"technique":[131],"mitigate":[133],"sparsity":[135],"further":[137],"improve":[138],"training.":[146],"Experiments":[147],"across":[148],"multiple":[149],"standard":[150],"benchmarks":[152],"demonstrate":[153],"achieves":[156],"state-of-the-art":[157],"performance":[158],"accelerating":[160],"reinforcement":[161],"tasks,":[165],"particularly":[166],"early":[169],"phase.":[171]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}