{"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":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2303.07551","any_repository_has_fulltext":true},"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"],"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"],"affiliations":[{"raw_affiliation_string":"Purdue University,Department of Computer Science,West Lafayette,IN,USA,47907","institution_ids":["https://openalex.org/I219193219"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":84},"biblio":{"volume":null,"issue":null,"first_page":"12942","last_page":"12948"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9893,"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":0.9893,"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":0.9891,"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":0.9308,"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/reinforcement-learning","display_name":"Reinforcement Learning","score":0.582967},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"Multi-Agent Systems","score":0.557927},{"id":"https://openalex.org/keywords/group-selection","display_name":"Group Selection","score":0.54283},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"Policy Gradient","score":0.541855},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep Learning","score":0.512147}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6811162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6253148},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45749292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3645535},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.23726669},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16594589},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.119645834},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09328854}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2303.07551","pdf_url":"https://arxiv.org/pdf/2303.07551","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2303.07551","pdf_url":"https://arxiv.org/pdf/2303.07551","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.54}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":33,"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"],"related_works":["https://openalex.org/W4396701345","https://openalex.org/W4396696052","https://openalex.org/W4395014643","https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2382290278","https://openalex.org/W2376932109","https://openalex.org/W2358668433","https://openalex.org/W2001405890"],"abstract_inverted_index":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4401415850","counts_by_year":[],"updated_date":"2024-12-04T20:20:08.663098","created_date":"2024-08-09"}