{"id":"https://openalex.org/W4401415850","doi":"https://doi.org/10.1109/icra57147.2024.10610919","title":"Merging Decision Transformers: Weight Averaging for Forming Multi-Task Policies","display_name":"Merging Decision Transformers: Weight Averaging for Forming Multi-Task Policies","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401415850","doi":"https://doi.org/10.1109/icra57147.2024.10610919"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610919","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5110693765","display_name":"Daniel E. Lawson","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Lawson","raw_affiliation_strings":["Purdue University,Department of Computer Science,West Lafayette,IN,USA,47907"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Department of Computer Science,West Lafayette,IN,USA,47907","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056336556","display_name":"Ahmed H. Qureshi","orcid":"https://orcid.org/0000-0003-2104-2333"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed H. Qureshi","raw_affiliation_strings":["Purdue University,Department of Computer Science,West Lafayette,IN,USA,47907"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Department of Computer Science,West Lafayette,IN,USA,47907","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":1.541,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.851332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12942","last_page":"12948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9890999794006348,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9308000206947327,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6811162233352661},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6253147721290588},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4574929177761078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3645535111427307},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.2372666895389557},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1659458875656128},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11964583396911621},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09328854084014893}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6811162233352661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6253147721290588},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4574929177761078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3645535111427307},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2372666895389557},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1659458875656128},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11964583396911621},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09328854084014893}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610919","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2560647685","https://openalex.org/W3016525976","https://openalex.org/W3117215073","https://openalex.org/W3134307371","https://openalex.org/W3169291081","https://openalex.org/W3198675127","https://openalex.org/W4221155125","https://openalex.org/W4226037452","https://openalex.org/W4226405181","https://openalex.org/W4226435594","https://openalex.org/W4281663178","https://openalex.org/W4286224767","https://openalex.org/W4286856923","https://openalex.org/W4286906081","https://openalex.org/W4291220705","https://openalex.org/W4295689550","https://openalex.org/W4298422451","https://openalex.org/W4300886482","https://openalex.org/W4307073393","https://openalex.org/W4309216950","https://openalex.org/W4309577790","https://openalex.org/W4310421358","https://openalex.org/W4310998073","https://openalex.org/W4312089761","https://openalex.org/W4318619660","https://openalex.org/W4319165322","https://openalex.org/W4385245566","https://openalex.org/W4385430825","https://openalex.org/W4385572602","https://openalex.org/W4386075549","https://openalex.org/W4386566605","https://openalex.org/W4389665702","https://openalex.org/W6846646240"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Recent":[0],"work":[1],"has":[2],"shown":[3],"the":[4,88,127],"promise":[5],"of":[6,33,67,90],"creating":[7],"generalist,":[8],"transformer-based,":[9],"models":[10,81],"for":[11,110],"language,":[12],"vision,":[13],"and":[14,29,106,125],"sequential":[15],"decision-making":[16],"problems.":[17],"To":[18],"create":[19,40],"such":[20,97],"models,":[21],"we":[22,36,54,116],"generally":[23],"require":[24],"centralized":[25,83],"training":[26],"objectives,":[27],"data,":[28],"compute.":[30],"It":[31],"is":[32,136],"interest":[34],"if":[35],"can":[37],"more":[38],"flexibly":[39],"generalist":[41],"policies":[42],"by":[43],"merging":[44,95],"together":[45],"multiple,":[46],"task-specific,":[47],"individually":[48],"trained":[49,73],"policies.":[50,133],"In":[51,114],"this":[52,60,120],"work,":[53],"take":[55],"a":[56],"preliminary":[57],"step":[58],"in":[59,70,119],"direction":[61,121],"through":[62],"merging,":[63],"or":[64],"averaging,":[65],"subsets":[66],"Decision":[68],"Transformers":[69],"parameter":[71,112],"space":[72],"on":[74],"different":[75],"MuJoCo":[76],"locomotion":[77],"problems,":[78],"forming":[79],"multi-task":[80,131],"without":[82],"training.":[84],"We":[85],"also":[86],"demonstrate":[87],"importance":[89],"various":[91],"methodological":[92],"choices":[93],"when":[94],"policies,":[96],"as":[98],"utilizing":[99,107],"common":[100],"pre-trained":[101],"initializations,":[102],"increasing":[103],"model":[104],"capacity,":[105],"Fisher":[108],"information":[109],"weighting":[111],"importance.":[113],"general,":[115],"believe":[117],"research":[118],"could":[122],"help":[123],"democratize":[124],"distribute":[126],"process":[128],"that":[129],"forms":[130],"robotics":[132],"Our":[134],"implementation":[135],"available":[137],"at":[138],"https://github.com/daniellawson9999/merging-decision-transformer.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}