{"id":"https://openalex.org/W4405785379","doi":"https://doi.org/10.1109/iros58592.2024.10802167","title":"Offline Meta-Reinforcement Learning with Evolving Gradient Agreement","display_name":"Offline Meta-Reinforcement Learning with Evolving Gradient Agreement","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785379","doi":"https://doi.org/10.1109/iros58592.2024.10802167"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":"https://openalex.org/A5100685937","display_name":"Jiaxing Chen","orcid":"https://orcid.org/0000-0003-4518-0941"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaxing Chen","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090802334","display_name":"Weilin Yuan","orcid":"https://orcid.org/0000-0001-9894-5253"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weilin Yuan","raw_affiliation_strings":["National University of Defense Technology,College of Information and Communication,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Information and Communication,Wuhan,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114155259","display_name":"S. L. Chen","orcid":"https://orcid.org/0000-0001-6823-555X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Chen","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027206778","display_name":"Furong Liu","orcid":"https://orcid.org/0009-0003-9145-8972"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Furong Liu","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066028121","display_name":"Ao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ao Ma","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040235604","display_name":"Zhenzhen Hu","orcid":"https://orcid.org/0000-0003-1042-8361"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhen Hu","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100432722","display_name":"Peng Li","orcid":"https://orcid.org/0000-0002-5983-2384"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Li","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100685937"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22186139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11893","last_page":"11900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8945000171661377,"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":0.8945000171661377,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7998263239860535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5891202092170715},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.5441452264785767},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.47216030955314636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4448167681694031},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12193071842193604},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10529819130897522},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06050178408622742}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7998263239860535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5891202092170715},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.5441452264785767},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47216030955314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4448167681694031},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12193071842193604},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10529819130897522},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06050178408622742},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W3134395475","https://openalex.org/W4312125978","https://openalex.org/W4312352946","https://openalex.org/W4312559878","https://openalex.org/W4386712244"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2891227010"],"abstract_inverted_index":{"Meta-Reinforcement":[0],"Learning":[1],"(Meta-RL)":[2],"is":[3,102],"a":[4,48,72],"machine":[5],"learning":[6,10,12,53],"paradigm":[7],"aimed":[8],"at":[9],"reinforcement":[11],"policies":[13,54],"that":[14,58,151],"can":[15,59],"quickly":[16],"adapt":[17,63],"to":[18,27,33,64,89,93,104,159],"unseen":[19,65,96,160],"tasks":[20],"with":[21,79],"few-shot":[22],"data.":[23],"Nevertheless,":[24],"applying":[25],"Meta-RL":[26,44,75],"real-world":[28,167],"applications":[29],"faces":[30],"challenges":[31],"due":[32],"the":[34,106,124,128,133],"cost":[35],"of":[36,127,135],"data":[37,57,140],"acquisition.":[38],"To":[39],"address":[40],"this":[41,68],"problem,":[42],"offline":[43,74,139],"has":[45],"emerged":[46],"as":[47,116],"promising":[49],"solution,":[50],"focusing":[51],"on":[52,145],"from":[55],"pre-collected":[56],"effectively":[60],"and":[61,109],"rapidly":[62],"tasks.":[66,97],"In":[67],"paper,":[69],"we":[70,112],"propose":[71],"new":[73],"method":[76],"called":[77],"Meta-Actor-Critic":[78],"Evolving":[80],"Gradient":[81],"Agreement":[82],"(MACEGA).":[83],"MACEGA":[84,136,152],"utilizes":[85],"an":[86,117],"evolutionary":[87],"approach":[88],"estimate":[90],"meta-gradients":[91],"conductive":[92],"generalization":[94,125],"across":[95],"During":[98],"meta-training,":[99],"gradient":[100,114],"evolution":[101],"utilized":[103],"meta-update":[105],"value":[107],"network":[108],"policies.":[110],"Moreover,":[111],"use":[113],"agreement":[115],"optimization":[118],"objective":[119],"for":[120,166],"meta-learning,":[121],"thereby":[122],"enhancing":[123],"ability":[126],"meta-policy.":[129],"We":[130],"experimentally":[131],"demonstrate":[132],"robustness":[134],"in":[137,157],"handling":[138],"quality.":[141],"Furthermore,":[142],"extensive":[143],"experiments":[144],"various":[146],"benchmarks":[147],"provide":[148],"empirical":[149],"evidence":[150],"outperforms":[153],"previous":[154],"state-of-the-art":[155],"methods":[156],"generalizing":[158],"tasks,":[161],"thus":[162],"demonstrating":[163],"its":[164],"potential":[165],"applications.":[168]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}