{"id":"https://openalex.org/W4361793646","doi":"https://doi.org/10.1145/3577530.3577562","title":"Policy Transfer via Skill Adaptation and Composition","display_name":"Policy Transfer via Skill Adaptation and Composition","publication_year":2022,"publication_date":"2022-12-09","ids":{"openalex":"https://openalex.org/W4361793646","doi":"https://doi.org/10.1145/3577530.3577562"},"language":"en","primary_location":{"id":"doi:10.1145/3577530.3577562","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577530.3577562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041871065","display_name":"Benhui Zhuang","orcid":"https://orcid.org/0000-0002-5062-2460"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Benhui Zhuang","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-5062-2460","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633263","display_name":"Chunhong Zhang","orcid":"https://orcid.org/0000-0003-3008-1887"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhong Zhang","raw_affiliation_strings":["Key Laboratory of Universal Wireless Communications, Beijing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0003-3008-1887","affiliations":[{"raw_affiliation_string":"Key Laboratory of Universal Wireless Communications, Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075198788","display_name":"Zheng Hu","orcid":"https://orcid.org/0000-0002-8874-5466"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Hu","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-8874-5466","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.995199978351593,"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/T12676","display_name":"Machine Learning and ELM","score":0.9891999959945679,"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/computer-science","display_name":"Computer science","score":0.7929400205612183},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7804025411605835},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7360537052154541},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6583020687103271},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6318264007568359},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6168708801269531},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6129969954490662},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.569580078125},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4909694492816925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.465372771024704},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4472542405128479},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.41403234004974365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37328195571899414},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3622656464576721},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11434569954872131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929400205612183},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7804025411605835},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7360537052154541},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6583020687103271},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6318264007568359},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6168708801269531},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6129969954490662},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.569580078125},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4909694492816925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.465372771024704},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4472542405128479},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.41403234004974365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37328195571899414},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3622656464576721},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11434569954872131},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3577530.3577562","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577530.3577562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2051228319","https://openalex.org/W2145339207","https://openalex.org/W3199572097","https://openalex.org/W3200711617","https://openalex.org/W4213052788","https://openalex.org/W4229044820"],"related_works":["https://openalex.org/W2384475851","https://openalex.org/W2000444236","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2353602216","https://openalex.org/W2024136090"],"abstract_inverted_index":{"While":[0],"reinforcement":[1],"learning":[2,24,44],"is":[3,38,72],"generally":[4],"powerful":[5],"on":[6,16,129,141],"decision":[7],"making,":[8],"it":[9],"usually":[10],"suffers":[11],"from":[12,29,58,147],"slow":[13],"convergence":[14],"rate":[15],"complex":[17],"problems.":[18],"Enlightened":[19],"by":[20,53],"human":[21],"experience,":[22],"transfer":[23,52],"that":[25,99,134],"reuses":[26],"skills":[27,56,76,109,113,119],"learned":[28,57],"the":[30,43,59,68,78,117,121,135,138,144],"source":[31,60,81],"task":[32,37,61,124,153],"to":[33,40,74,77,116,143],"a":[34,91,101],"new":[35],"target":[36,69,83],"desirable":[39],"speed":[41],"up":[42],"process.":[45],"However,":[46],"most":[47],"existing":[48],"works":[49],"achieve":[50],"policy":[51,103],"reusing":[54],"fixed":[55],"and":[62,82,110,152],"simply":[63],"recomposing":[64],"them":[65],"linearly":[66],"in":[67,114],"task,":[70],"which":[71],"inefficient":[73],"adapt":[75],"differences":[79,146],"between":[80],"tasks.":[84],"To":[85],"address":[86],"this":[87],"issue,":[88],"we":[89],"propose":[90],"framework,":[92],"Pre-Trained":[93],"Hierarchical":[94],"Recurrent":[95],"Independent":[96],"Mechanisms":[97],"(PHRIM),":[98],"optimizes":[100],"hierarchical":[102],"for":[104,120],"selective":[105],"composition":[106],"of":[107,123,149],"modular":[108],"learns":[111],"adaptive":[112],"addition":[115],"transferred":[118],"adaptation":[122],"differences.":[125],"The":[126],"experiment":[127],"conducted":[128],"MiniGrid":[130],"maze":[131],"game":[132],"demonstrates":[133],"PHRIM":[136],"outperforms":[137],"fixed-skill":[139],"baselines":[140],"adapting":[142],"source-to-target":[145],"aspects":[148],"state,":[150],"action,":[151],"complexity":[154],"respectively.":[155]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}