{"id":"https://openalex.org/W4391766438","doi":"https://doi.org/10.48550/arxiv.2402.06102","title":"Real-World Fluid Directed Rigid Body Control via Deep Reinforcement Learning","display_name":"Real-World Fluid Directed Rigid Body Control via Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-02-08","ids":{"openalex":"https://openalex.org/W4391766438","doi":"https://doi.org/10.48550/arxiv.2402.06102"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2402.06102","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.06102","pdf_url":"https://arxiv.org/pdf/2402.06102","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":null,"license_id":null,"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/2402.06102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017774267","display_name":"Mohak Bhardwaj","orcid":"https://orcid.org/0000-0002-4775-8113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhardwaj, Mohak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054636066","display_name":"Thomas Lampe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lampe, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053312475","display_name":"Michael Neunert","orcid":"https://orcid.org/0000-0003-2080-8376"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neunert, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503909","display_name":"Francesco Roman\u00f2","orcid":"https://orcid.org/0000-0001-5630-4992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romano, Francesco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007133617","display_name":"Abbas Abdolmaleki","orcid":"https://orcid.org/0000-0001-6692-5856"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdolmaleki, Abbas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037305533","display_name":"Arunkumar Byravan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byravan, Arunkumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002747297","display_name":"Markus Wulfmeier","orcid":"https://orcid.org/0000-0003-1802-4492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wulfmeier, Markus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041323275","display_name":"Martin Riedmiller","orcid":"https://orcid.org/0000-0002-8465-5690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Riedmiller, Martin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077279214","display_name":"Jonas Buchli","orcid":"https://orcid.org/0000-0001-7494-8492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Buchli, Jonas","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":true,"cited_by_count":0,"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/T11687","display_name":"Teleoperation and Haptic Systems","score":0.9509999752044678,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11687","display_name":"Teleoperation and Haptic Systems","score":0.9509999752044678,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.90420001745224,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9025999903678894,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.6244214773178101},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.48312947154045105},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44287368655204773},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42241600155830383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4102005958557129},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20553341507911682},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.1074724793434143}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6244214773178101},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.48312947154045105},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44287368655204773},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42241600155830383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4102005958557129},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20553341507911682},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.1074724793434143}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2402.06102","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.06102","pdf_url":"https://arxiv.org/pdf/2402.06102","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.06102","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.06102","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.06102","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.06102","pdf_url":"https://arxiv.org/pdf/2402.06102","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391766438.pdf","grobid_xml":"https://content.openalex.org/works/W4391766438.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,75,120],"real-world":[3,77],"applications":[4],"of":[5,44,84,93,105,117,141,170],"reinforcement":[6],"learning":[7],"(RL)":[8],"have":[9],"relied":[10],"on":[11],"the":[12,41,81,85,115,131,139,144,149],"ability":[13],"to":[14,34,49,162],"accurately":[15],"simulate":[16,35],"systems":[17,26,142],"at":[18,36,174],"scale.":[19],"However,":[20],"domains":[21],"such":[22],"as":[23],"fluid":[24],"dynamical":[25,164],"exhibit":[27],"complex":[28,106],"dynamic":[29,76],"phenomena":[30],"that":[31,130,157],"are":[32,172],"hard":[33],"high":[37],"integration":[38],"rates,":[39],"limiting":[40],"direct":[42],"application":[43],"modern":[45],"deep":[46],"RL":[47,73,99,119,155],"algorithms":[48,74,100,156],"often":[50],"expensive":[51],"or":[52],"safety":[53],"critical":[54],"hardware.":[55],"In":[56],"this":[57,135],"work,":[58],"we":[59,113],"introduce":[60],"\"Box":[61],"o":[62,87,146],"Flows\",":[63],"a":[64,91,103],"novel":[65],"benchtop":[66],"experimental":[67],"control":[68],"system":[69],"for":[70,152],"systematically":[71],"evaluating":[72],"scenarios.":[78],"We":[79,128],"describe":[80],"key":[82],"components":[83],"Box":[86,145],"Flows,":[88],"and":[89,138,168],"through":[90],"series":[92],"experiments":[94,171],"demonstrate":[95],"how":[96],"state-of-the-art":[97],"model-free":[98],"can":[101,158],"synthesize":[102],"variety":[104],"behaviors":[107],"via":[108],"simple":[109],"reward":[110],"specifications.":[111],"Furthermore,":[112],"explore":[114],"role":[116],"offline":[118],"data-efficient":[121],"hypothesis":[122],"testing":[123],"by":[124],"reusing":[125],"past":[126],"experiences.":[127],"believe":[129],"insights":[132],"gained":[133],"from":[134],"preliminary":[136],"study":[137],"availability":[140],"like":[143],"Flows":[147],"support":[148],"way":[150],"forward":[151],"developing":[153],"systematic":[154],"be":[159],"generally":[160],"applied":[161],"complex,":[163],"systems.":[165],"Supplementary":[166],"material":[167],"videos":[169],"available":[173],"https://sites.google.com/view/box-o-flows/home.":[175]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}