{"id":"https://openalex.org/W7213879486","doi":"https://doi.org/10.6084/m9.figshare.33959761","title":"Sample-Efficient Model-Based Reinforcement Learning for Autonomous Droplet Navigation via Controller Initialization","display_name":"Sample-Efficient Model-Based Reinforcement Learning for Autonomous Droplet Navigation via Controller Initialization","publication_year":2026,"publication_date":"2026-09-21","ids":{"openalex":"https://openalex.org/W7213879486","doi":"https://doi.org/10.6084/m9.figshare.33959761"},"language":"en","primary_location":{"id":"doi:10.6084/m9.figshare.33959761","doi":"https://doi.org/10.6084/m9.figshare.33959761","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.33959761","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.6084/m9.figshare.33959761","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151921131","display_name":"Rajneesh Anand","orcid":"https://orcid.org/0000-0002-5465-841X","observed_orcids":["https://orcid.org/0000-0002-5465-841X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajneesh Anand","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152362373","display_name":"Fatima Tanveer","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fatima Tanveer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023162180","display_name":"Mayuresh V. Kothare","orcid":"https://orcid.org/0000-0001-7681-7445","observed_orcids":["https://orcid.org/0000-0001-7681-7445"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mayuresh V. Kothare","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":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/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"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"}},{"id":"https://openalex.org/T12452","display_name":"Electrowetting and Microfluidic Technologies","score":0.0,"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/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.8939999938011169},{"id":"https://openalex.org/keywords/controller-initialization","display_name":"controller initialization","score":0.7390000224113464},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.628000020980835},{"id":"https://openalex.org/keywords/liquid-droplets","display_name":"droplets","score":0.5580000281333923},{"id":"https://openalex.org/keywords/microrobots","display_name":"microrobots","score":0.7059999704360962},{"id":"https://openalex.org/keywords/data-collection-costs","display_name":"data collection costs","score":0.5680000185966492},{"id":"https://openalex.org/keywords/rollout","display_name":"rollout","score":0.3930000066757202},{"id":"https://openalex.org/keywords/deformable-droplets","display_name":"deformable droplets","score":0.38600000739097595}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.9132000207901001},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.675599992275238},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.645799994468689},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6234999895095825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.616100013256073},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5557000041007996},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.376800000667572},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.37310001254081726},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C2779199153","wikidata":"https://www.wikidata.org/wiki/Q43965","display_name":"Quadcopter","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26350000500679016},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.6084/m9.figshare.33959761","doi":"https://doi.org/10.6084/m9.figshare.33959761","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.33959761","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},{"id":"doi:10.6084/m9.figshare.33959761.v1","doi":"https://doi.org/10.6084/m9.figshare.33959761.v1","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.33959761.v1","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.6084/m9.figshare.33959761","doi":"https://doi.org/10.6084/m9.figshare.33959761","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.33959761","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7220896622","https://openalex.org/W2966961840","https://openalex.org/W7213431685","https://openalex.org/W3005127431","https://openalex.org/W3154987973","https://openalex.org/W3096519373","https://openalex.org/W4393177974","https://openalex.org/W2963781688","https://openalex.org/W3189906240","https://openalex.org/W4409560189"],"abstract_inverted_index":{"Model-based":[0],"reinforcement":[1],"learning":[2],"(MBRL)":[3],"is":[4,92],"well":[5],"suited":[6],"to":[7,67],"controlling":[8],"physical":[9,97,138],"systems":[10,155],"that":[11,44],"resist":[12],"analytical":[13],"modeling,":[14],"but":[15],"its":[16],"reliance":[17],"on":[18,35,38,49,95,156],"real-world":[19],"interaction":[20],"makes":[21],"data":[22],"collection":[23],"the":[24,30,96,107,118,126,135],"dominant":[25],"cost.":[26],"This":[27,143],"paper":[28],"quantifies":[29],"effect":[31],"of":[32,86,137],"initialization":[33,124,132],"choice":[34],"this":[36],"cost,":[37],"a":[39,46,50,145,150],"newly":[40],"adapted":[41],"robotic":[42],"platform":[43],"guides":[45],"liquid":[47,58],"droplet":[48],"tilt-actuated":[51],"Labyrinth":[52],"using":[53],"MBRL.":[54],"Unlike":[55],"rigid":[56],"microrobots,":[57],"droplets":[59],"exhibit":[60],"deformability":[61],"and":[62,70,102,115],"pinning,":[63],"rendering":[64],"their":[65],"response":[66],"actuation":[68],"nonlinear":[69],"history-dependent.":[71],"A":[72],"closed-loop":[73],"gain-tuned":[74],"PID":[75,121,123],"controller,":[76],"individually":[77],"optimized":[78],"per":[79],"geometry,":[80],"succeeds":[81],"in":[82],"at":[83],"most":[84],"one":[85],"five":[87],"trials.":[88],"The":[89],"control":[90],"policy":[91],"learned":[93],"directly":[94],"system,":[98],"with":[99],"no":[100],"simulator,":[101],"two":[103],"schemes":[104],"for":[105,153],"seeding":[106],"world":[108],"model":[109],"are":[110],"compared,":[111],"namely":[112],"random":[113,131],"exploration":[114],"rollouts":[116],"from":[117],"same":[119,127],"tuned":[120],"controller.":[122],"reaches":[125],"terminal":[128],"success":[129],"as":[130,149],"while":[133],"reducing":[134],"number":[136],"training":[139],"episodes":[140],"by":[141],"30-50%.":[142],"repurposes":[144],"weak":[146],"classical":[147],"controller":[148],"sample-efficient":[151],"prior":[152],"hard-to-model":[154],"costly":[157],"hardware.":[158]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-22T00:00:00"}