{"id":"https://openalex.org/W4379983844","doi":"https://doi.org/10.1109/lra.2023.3284660","title":"Efficient Multi-Task and Transfer Reinforcement Learning With Parameter-Compositional Framework","display_name":"Efficient Multi-Task and Transfer Reinforcement Learning With Parameter-Compositional Framework","publication_year":2023,"publication_date":"2023-06-09","ids":{"openalex":"https://openalex.org/W4379983844","doi":"https://doi.org/10.1109/lra.2023.3284660"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3284660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3284660","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5065597482","display_name":"Lingfeng Sun","orcid":"https://orcid.org/0000-0002-1134-4103"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lingfeng Sun","raw_affiliation_strings":["School of Mechanical Engineering, University of California, Berkeley, Albany, CA, USA"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, University of California, Berkeley, Albany, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101758339","display_name":"Haichao Zhang","orcid":"https://orcid.org/0000-0002-3276-3390"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haichao Zhang","raw_affiliation_strings":["Horizon Robotics, Cupertino, CA, USA"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics, Cupertino, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407852","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-1960-0992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["Horizon Robotics, Cupertino, CA, USA"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics, Cupertino, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064077634","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masayoshi Tomizuka","raw_affiliation_strings":["School of Mechanical Engineering, University of California, Berkeley, Albany, CA, USA"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, University of California, Berkeley, Albany, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065597482"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":1.226,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82890284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"8","issue":"8","first_page":"4569","last_page":"4576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9898999929428101,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8888804912567139},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7720311880111694},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7683039903640747},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6464848518371582},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6172952651977539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5298872590065002},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5172441601753235},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4849450886249542},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.48280107975006104},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4395008981227875},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07918259501457214}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8888804912567139},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7720311880111694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7683039903640747},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6464848518371582},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6172952651977539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5298872590065002},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5172441601753235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4849450886249542},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.48280107975006104},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4395008981227875},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07918259501457214},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3284660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3284660","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1673310716","https://openalex.org/W2097381042","https://openalex.org/W2181252817","https://openalex.org/W2440926996","https://openalex.org/W2591924527","https://openalex.org/W2604763608","https://openalex.org/W2620290674","https://openalex.org/W2735995851","https://openalex.org/W2760103357","https://openalex.org/W2781726626","https://openalex.org/W2804935296","https://openalex.org/W2896457183","https://openalex.org/W2913485808","https://openalex.org/W2964262254","https://openalex.org/W2981344907","https://openalex.org/W2995049146","https://openalex.org/W2995481444","https://openalex.org/W3013821552","https://openalex.org/W3046419021","https://openalex.org/W3106539628","https://openalex.org/W3132818773","https://openalex.org/W3191738967","https://openalex.org/W3205433563","https://openalex.org/W3207349876","https://openalex.org/W4283313139","https://openalex.org/W4287113380","https://openalex.org/W4287209565","https://openalex.org/W4287329474","https://openalex.org/W4293872189","https://openalex.org/W4297669644","https://openalex.org/W4298174377","https://openalex.org/W4300799055","https://openalex.org/W4307204265","https://openalex.org/W4362655350","https://openalex.org/W6637131181","https://openalex.org/W6674600207","https://openalex.org/W6685726866","https://openalex.org/W6718190810","https://openalex.org/W6730038592","https://openalex.org/W6736057607","https://openalex.org/W6738165965","https://openalex.org/W6740801417","https://openalex.org/W6740879895","https://openalex.org/W6747473740","https://openalex.org/W6748599296","https://openalex.org/W6755207826","https://openalex.org/W6758885689","https://openalex.org/W6768532476","https://openalex.org/W6769596995","https://openalex.org/W6771876938","https://openalex.org/W6775647304","https://openalex.org/W6781494318","https://openalex.org/W6790190981","https://openalex.org/W6791065048","https://openalex.org/W6793853427","https://openalex.org/W6797394732","https://openalex.org/W6802551040","https://openalex.org/W6846476806","https://openalex.org/W6851566003"],"related_works":["https://openalex.org/W2821676139","https://openalex.org/W3043695725","https://openalex.org/W4382138864","https://openalex.org/W3022215768","https://openalex.org/W4387770285","https://openalex.org/W3135975972","https://openalex.org/W3016888008","https://openalex.org/W4385864216","https://openalex.org/W4387183713","https://openalex.org/W2165698076"],"abstract_inverted_index":{"In":[0],"this":[1,27],"work,":[2],"we":[3,57],"investigate":[4,39],"the":[5,18,43,52,72,80],"potential":[6],"of":[7,45,61,91],"improving":[8],"multi-task":[9,46,81],"training":[10,44,82],"and":[11,29,84,95],"also":[12],"leveraging":[13],"it":[14],"for":[15,54],"transferring":[16,32,62,88],"in":[17,79,89],"reinforcement":[19,47],"learning":[20,48],"setting.":[21],"We":[22,38],"identify":[23],"several":[24],"challenges":[25],"towards":[26],"goal":[28],"propose":[30],"a":[31,35,59],"approach":[33,74],"with":[34],"parameter-compositional":[36],"formulation.":[37],"ways":[40],"to":[41],"improve":[42],"which":[49],"serves":[50],"as":[51],"foundation":[53],"transferring.":[55],"Then":[56],"conduct":[58],"number":[60],"experiments":[63],"on":[64],"various":[65],"manipulation":[66],"tasks.":[67],"Experimental":[68],"results":[69],"demonstrate":[70],"that":[71],"proposed":[73],"can":[75],"have":[76],"improved":[77],"performance":[78],"stage,":[83],"further":[85],"show":[86],"effective":[87],"terms":[90],"both":[92],"sample":[93],"efficiency":[94],"performance.":[96]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}