{"id":"https://openalex.org/W4402351463","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650992","title":"Enhancing Offline Reinforcement Learning via Dynamics-Aware Mixup","display_name":"Enhancing Offline Reinforcement Learning via Dynamics-Aware Mixup","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351463","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650992"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650992","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5030395145","display_name":"Chang Tan","orcid":"https://orcid.org/0000-0002-7707-1531"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Tan","raw_affiliation_strings":["Jilin University,College of Software,Changchun,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University,College of Software,Changchun,China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109778654","display_name":"Yunjie Su","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjie Su","raw_affiliation_strings":["Tsinghua University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090915513","display_name":"Jiaao Wang","orcid":"https://orcid.org/0000-0002-4944-4951"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaao Wang","raw_affiliation_strings":["Tsinghua University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.14597346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8587085604667664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7515614032745361},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5842584371566772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4630546569824219},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42337560653686523}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8587085604667664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7515614032745361},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5842584371566772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4630546569824219},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42337560653686523},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650992","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/W1551558821","https://openalex.org/W2112420033","https://openalex.org/W2158782408","https://openalex.org/W2747329762","https://openalex.org/W2765407302","https://openalex.org/W2947150733","https://openalex.org/W2963411833","https://openalex.org/W2978455699","https://openalex.org/W2982041329","https://openalex.org/W2991355586","https://openalex.org/W2993185773","https://openalex.org/W3007369745","https://openalex.org/W3016525976","https://openalex.org/W3021708257","https://openalex.org/W3022566517","https://openalex.org/W3025606523","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3034084488","https://openalex.org/W3088304681","https://openalex.org/W3094044532","https://openalex.org/W3097907450","https://openalex.org/W3125947392","https://openalex.org/W3172360140","https://openalex.org/W3172628684","https://openalex.org/W3201700917","https://openalex.org/W3202125656","https://openalex.org/W3205279445","https://openalex.org/W3211444363","https://openalex.org/W4225110331","https://openalex.org/W4252279978","https://openalex.org/W4283076713","https://openalex.org/W4287756699","https://openalex.org/W4288319859","https://openalex.org/W4298857966","https://openalex.org/W4306177351","https://openalex.org/W4306295204","https://openalex.org/W4360584316","https://openalex.org/W4385482619","https://openalex.org/W6757469721","https://openalex.org/W6764053384","https://openalex.org/W6769342953","https://openalex.org/W6774583691","https://openalex.org/W6776867236","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6784098896","https://openalex.org/W6788972952","https://openalex.org/W6791413555","https://openalex.org/W6792049622","https://openalex.org/W6795014841","https://openalex.org/W6796589144","https://openalex.org/W6798709053","https://openalex.org/W6801728237","https://openalex.org/W6810277566","https://openalex.org/W6838958960","https://openalex.org/W6845414265","https://openalex.org/W6846333248"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"One":[0],"of":[1,18,34,40,68,101,115,137,175,219],"the":[2,19,22,32,56,65,69,80,99,102,113,134,138,150,154,162,173,176,181,185,192,200,208,217],"principal":[3],"challenges":[4],"in":[5,11,59,73,88,118],"Offline":[6,89,104,119,222],"Reinforcement":[7],"Learning":[8],"(RL)":[9],"lies":[10],"its":[12],"inability":[13],"to":[14,27,31,36,64,86,125,148,180,190,198],"conduct":[15],"further":[16,97],"exploration":[17],"environment,":[20],"and":[21,43,96,111,128,157,184,195,202,225],"existing":[23,220],"models":[24],"may":[25,91],"struggle":[26],"effectively":[28,54],"respond":[29],"due":[30,63],"lack":[33],"exposure":[35],"a":[37,50,145],"broader":[38],"range":[39],"environmental":[41],"states":[42,163],"actions":[44],"during":[45],"training.":[46],"Data":[47],"augmentation":[48,117],"is":[49,188],"proven":[51],"method":[52,214],"for":[53],"reducing":[55],"generalization":[57],"gap":[58],"offline":[60,75],"reinforcement":[61],"learning,":[62],"limited":[66],"coverage":[67],"full":[70],"state-action":[71],"space":[72],"static":[74,168],"datasets.":[76],"However,":[77],"naively":[78],"applying":[79],"interpolation-based":[81],"augmentation,":[82],"such":[83],"as":[84,167],"Mixup,":[85],"transitions":[87,95,166],"RL":[90,105,139,223],"generate":[92,126],"semantically":[93],"meaningless":[94],"downgrade":[98],"performance":[100,218],"underlying":[103],"method.":[106],"To":[107],"tackle":[108],"this":[109],"issue":[110],"take":[112],"advantages":[114],"data":[116,131],"RL,":[120],"we":[121,142],"propose":[122],"Dynamics-Aware":[123],"Mixup":[124],"diverse":[127],"meaningful":[129],"augmented":[130],"by":[132],"considering":[133],"inherent":[135],"dynamics":[136,146,186],"system.":[140],"Specifically,":[141],"first":[143],"maintain":[144],"model":[147,187],"characterize":[149],"environment":[151],"based":[152],"on":[153,207],"logged":[155],"dataset,":[156],"then":[158,171],"only":[159],"mix":[160],"up":[161],"from":[164],"two":[165],"exploration.":[169],"We":[170],"determine":[172],"action":[174],"generated":[177],"state":[178,194],"according":[179],"policy":[182],"directly,":[183],"used":[189],"predict":[191],"next":[193],"reward":[196],"information":[197],"create":[199],"new":[201],"complete":[203],"transition.":[204],"Experimental":[205],"results":[206],"D4RL":[209],"benchmarks":[210],"demonstrate":[211],"that":[212],"our":[213],"significantly":[215],"boosts":[216],"model-free":[221],"algorithms":[224],"achieves":[226],"competitive":[227],"scores.":[228]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}