{"id":"https://openalex.org/W4416749897","doi":"https://doi.org/10.1109/iros60139.2025.11246876","title":"Leveraging Temporally Extended Behavior Sharing for Multi-task Reinforcement Learning","display_name":"Leveraging Temporally Extended Behavior Sharing for Multi-task Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749897","doi":"https://doi.org/10.1109/iros60139.2025.11246876"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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":null,"display_name":"Gawon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gawon Lee","raw_affiliation_strings":["Seoul National University,Department of Aerospace Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Aerospace Engineering","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032424238","display_name":"Daesol Cho","orcid":"https://orcid.org/0000-0002-4105-4422"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daesol Cho","raw_affiliation_strings":["Seoul National University,Artificial Intelligence Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Artificial Intelligence Institute","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044847367","display_name":"Hansom Kim","orcid":"https://orcid.org/0000-0003-1982-3579"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"H. Jin Kim","raw_affiliation_strings":["Seoul National University,Department of Aerospace Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Aerospace Engineering","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17505009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9768","last_page":"9775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9241999983787537,"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":0.9241999983787537,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.024399999529123306,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10982","display_name":"Motor Control and Adaptation","score":0.004600000102072954,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.734499990940094},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6700000166893005},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6338000297546387},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5726000070571899},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5171999931335449},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5113999843597412}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7581999897956848},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.734499990940094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6909999847412109},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6700000166893005},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6338000297546387},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5726000070571899},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5443999767303467},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C2776604539","wikidata":"https://www.wikidata.org/wiki/Q6423395","display_name":"Knowledge sharing","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32839998602867126},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2020920737","https://openalex.org/W2040675064","https://openalex.org/W2126861285","https://openalex.org/W2443711627","https://openalex.org/W2766447205","https://openalex.org/W2926474791","https://openalex.org/W2973229164","https://openalex.org/W3081310128","https://openalex.org/W3206200647","https://openalex.org/W4393147301","https://openalex.org/W4405710362","https://openalex.org/W4415566408","https://openalex.org/W4415795473"],"related_works":[],"abstract_inverted_index":{"Multi-task":[0],"reinforcement":[1],"learning":[2],"(MTRL)":[3],"offers":[4],"a":[5,48],"promising":[6],"approach":[7,98],"to":[8,28,33,81],"improve":[9,146],"sample":[10,54,118],"efficiency":[11,55],"and":[12,117,123],"generalization":[13],"by":[14,59,70,121],"training":[15],"agents":[16],"across":[17,63],"multiple":[18],"tasks,":[19],"enabling":[20],"knowledge":[21],"sharing":[22,62,139],"between":[23],"them.":[24],"However,":[25],"applying":[26],"MTRL":[27,57,150],"robotics":[29,107,152],"remains":[30],"challenging":[31],"due":[32],"the":[34,130,147],"high":[35],"cost":[36],"of":[37,132,149],"collecting":[38],"diverse":[39],"task":[40,94],"data.":[41],"To":[42],"address":[43],"this,":[44],"we":[45],"propose":[46],"MT-L\u00e9vy,":[47],"novel":[49],"exploration":[50,68,83,90,116,142],"strategy":[51],"that":[52,112,136],"enhances":[53],"in":[56,105,151],"environments":[58],"combining":[60,137],"behavior":[61,138],"tasks":[64,80],"with":[65,140],"temporally":[66],"extended":[67],"inspired":[69],"L\u00e9vy":[71],"flight":[72],"[1].":[73],"MT-L\u00e9vy":[74,113],"leverages":[75],"policies":[76],"trained":[77],"on":[78,93],"related":[79],"guide":[82],"towards":[84],"key":[85],"states,":[86],"while":[87],"dynamically":[88],"adjusting":[89],"levels":[91],"based":[92],"success":[95],"ratios.":[96],"This":[97],"enables":[99],"more":[100],"efficient":[101],"state-space":[102],"coverage,":[103],"even":[104],"complex":[106],"environments.":[108],"Empirical":[109],"results":[110],"demonstrate":[111],"significantly":[114,145],"improves":[115],"efficiency,":[119],"supported":[120],"quantitative":[122],"qualitative":[124],"analyses.":[125],"Ablation":[126],"studies":[127],"further":[128],"highlight":[129],"contribution":[131],"each":[133],"component,":[134],"showing":[135],"adaptive":[141],"strategies":[143],"can":[144],"practicality":[148],"applications.":[153]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}