{"id":"https://openalex.org/W4320558428","doi":"https://doi.org/10.48550/arxiv.2302.04903","title":"AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfer","display_name":"AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfer","publication_year":2023,"publication_date":"2023-02-09","ids":{"openalex":"https://openalex.org/W4320558428","doi":"https://doi.org/10.48550/arxiv.2302.04903"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2302.04903","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.04903","pdf_url":"https://arxiv.org/pdf/2302.04903","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.04903","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000576583","display_name":"Allen Z. Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Allen Z.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039615570","display_name":"Hongkai Dai","orcid":"https://orcid.org/0000-0002-6131-3620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Hongkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091048694","display_name":"Benjamin Burchfiel","orcid":"https://orcid.org/0000-0001-7332-6712"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Burchfiel, Benjamin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102792178","display_name":"Anirudha Majumdar","orcid":"https://orcid.org/0009-0002-2296-7485"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Majumdar, Anirudha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9811000227928162,"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":0.9811000227928162,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9538999795913696,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9431999921798706,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7300375699996948},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6503952741622925},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.593510091304779},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.49285078048706055},{"id":"https://openalex.org/keywords/dynamical-simulation","display_name":"Dynamical simulation","score":0.4482802748680115},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.33205655217170715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32467979192733765},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11203530430793762}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300375699996948},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6503952741622925},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.593510091304779},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.49285078048706055},{"id":"https://openalex.org/C81587630","wikidata":"https://www.wikidata.org/wiki/Q5319044","display_name":"Dynamical simulation","level":2,"score":0.4482802748680115},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.33205655217170715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32467979192733765},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11203530430793762},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2302.04903","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.04903","pdf_url":"https://arxiv.org/pdf/2302.04903","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2302.04903","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2302.04903","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.04903","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.04903","pdf_url":"https://arxiv.org/pdf/2302.04903","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","score":0.46000000834465027,"display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W4391331176"],"abstract_inverted_index":{"Simulation":[0],"parameter":[1,141,163],"settings":[2],"such":[3,32],"as":[4],"contact":[5],"models":[6],"and":[7,59,68,73,78,124,195,208,217,233],"object":[8],"geometry":[9],"approximations":[10],"are":[11],"critical":[12],"to":[13,23,62,82,109,224,228],"training":[14,235],"robust":[15],"robotic":[16,180],"policies":[17,83],"capable":[18],"of":[19,44,119,172,184,192,199],"transferring":[20],"from":[21],"simulation":[22,58,67,123,133,140,162,207],"real-world":[24,157],"deployment.":[25],"Previous":[26],"approaches":[27],"typically":[28],"handcraft":[29],"distributions":[30,164],"over":[31],"parameters":[33,38],"(domain":[34],"randomization),":[35],"or":[36],"identify":[37],"that":[39,84,107],"best":[40],"match":[41,63],"the":[42,45,64,139,145,236],"dynamics":[43,65,121],"real":[46,173,219],"environment":[47],"(system":[48],"identification).":[49],"However,":[50],"there":[51],"is":[52],"often":[53],"an":[54,129],"irreducible":[55],"gap":[56],"between":[57,66,122],"reality:":[60],"attempting":[61],"reality":[69,88],"across":[70],"all":[71],"states":[72],"tasks":[74],"may":[75,79],"be":[76],"infeasible":[77],"not":[80],"lead":[81],"perform":[85,155,176],"well":[86],"in":[87,113,132,149,178,239],"for":[89,104,137,165],"a":[90,99,150,169,193,203],"specific":[91],"task.":[92],"Addressing":[93],"this":[94],"issue,":[95],"we":[96,127],"propose":[97],"AdaptSim,":[98],"new":[100,161],"task-driven":[101],"adaptation":[102,130,158],"framework":[103],"sim-to-real":[105],"transfer":[106],"aims":[108],"optimize":[110],"task":[111,237],"performance":[112,148,216],"target":[114,151,240],"(real)":[115],"environments":[116],"--":[117],"instead":[118],"matching":[120],"reality.":[125],"First,":[126],"meta-learn":[128],"policy":[131,166,238],"using":[134,168],"reinforcement":[135],"learning":[136],"adjusting":[138],"distribution":[142],"based":[143,230],"on":[144,231],"current":[146],"policy's":[147],"environment.":[152],"We":[153,175],"then":[154],"iterative":[156],"by":[159],"inferring":[160],"training,":[167],"small":[170],"amount":[171],"data.":[174],"experiments":[177,210],"three":[179],"tasks:":[181],"(1)":[182],"swing-up":[183],"linearized":[185],"double":[186],"pendulum,":[187],"(2)":[188],"dynamic":[189,197],"table-top":[190],"pushing":[191],"bottle,":[194],"(3)":[196],"scooping":[198],"food":[200],"pieces":[201],"with":[202],"spatula.":[204],"Our":[205],"extensive":[206],"hardware":[209],"demonstrate":[211],"AdaptSim":[212],"achieving":[213],"1-3x":[214],"asymptotic":[215],"$\\sim$2x":[218],"data":[220],"efficiency":[221],"when":[222],"adapting":[223],"different":[225],"environments,":[226],"compared":[227],"methods":[229],"Sys-ID":[232],"directly":[234],"environments.":[241],"Website:":[242],"https://irom-lab.github.io/AdaptSim/":[243]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}