{"id":"https://openalex.org/W2907704766","doi":"https://doi.org/10.1145/3493700.3493712","title":"An Active Learning Framework for Efficient Robust Policy Search","display_name":"An Active Learning Framework for Efficient Robust Policy Search","publication_year":2022,"publication_date":"2022-01-07","ids":{"openalex":"https://openalex.org/W2907704766","doi":"https://doi.org/10.1145/3493700.3493712","mag":"2907704766"},"language":"en","primary_location":{"id":"doi:10.1145/3493700.3493712","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493700.3493712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1901.00117","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003531741","display_name":"Sai Kiran Narayanaswami","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sai Kiran Narayanaswami","raw_affiliation_strings":["Indian Institute of Technology, Madras, IN"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Madras, IN","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000884616","display_name":"Nandan Sudarsanam","orcid":"https://orcid.org/0000-0002-1871-2917"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nandan Sudarsanam","raw_affiliation_strings":["Indian Institute of Technology - Madras, IN"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology - Madras, IN","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009374923","display_name":"Balaraman Ravindran","orcid":"https://orcid.org/0000-0002-5364-7639"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balaraman Ravindran","raw_affiliation_strings":["Indian Institute of Technology Madras, IN"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, IN","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003531741"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00245478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9988999962806702,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.8196470737457275},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6555557250976562},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6285815238952637},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.607019305229187},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5763212442398071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5580219626426697},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.47597306966781616},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.44596779346466064},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4315341114997864},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.42575401067733765},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08913636207580566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8196470737457275},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6555557250976562},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6285815238952637},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.607019305229187},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5763212442398071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5580219626426697},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47597306966781616},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.44596779346466064},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4315341114997864},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.42575401067733765},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08913636207580566},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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":2,"locations":[{"id":"doi:10.1145/3493700.3493712","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493700.3493712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1901.00117","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.00117","pdf_url":"https://arxiv.org/pdf/1901.00117","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1901.00117","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.00117","pdf_url":"https://arxiv.org/pdf/1901.00117","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1771410628","https://openalex.org/W1966784014","https://openalex.org/W2097381042","https://openalex.org/W2102665362","https://openalex.org/W2104733512","https://openalex.org/W2105078254","https://openalex.org/W2112420033","https://openalex.org/W2119738618","https://openalex.org/W2135664069","https://openalex.org/W2140135625","https://openalex.org/W2158782408","https://openalex.org/W2166253248","https://openalex.org/W2167696704","https://openalex.org/W2205975260","https://openalex.org/W2555558374","https://openalex.org/W2556958149","https://openalex.org/W2584377191","https://openalex.org/W2602963933","https://openalex.org/W2605102758","https://openalex.org/W2736601468","https://openalex.org/W2773557179","https://openalex.org/W2785389871","https://openalex.org/W2903158431","https://openalex.org/W2927638312","https://openalex.org/W2949608212","https://openalex.org/W2949963197","https://openalex.org/W2962858248","https://openalex.org/W2963095800","https://openalex.org/W2963184621","https://openalex.org/W2963488722","https://openalex.org/W2963614114","https://openalex.org/W2963645163","https://openalex.org/W2963846183","https://openalex.org/W2963864421","https://openalex.org/W2963906246","https://openalex.org/W2964173023","https://openalex.org/W2970325526","https://openalex.org/W3101442004","https://openalex.org/W4235001947","https://openalex.org/W4289464898","https://openalex.org/W4292651439","https://openalex.org/W4293579911","https://openalex.org/W4297824641","https://openalex.org/W4298174377","https://openalex.org/W4299286629","https://openalex.org/W4299364435","https://openalex.org/W4319988532","https://openalex.org/W4365800133","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W1975289146","https://openalex.org/W2770593030","https://openalex.org/W3154990682","https://openalex.org/W2560201613","https://openalex.org/W2171975302","https://openalex.org/W2022352247","https://openalex.org/W2105887828","https://openalex.org/W2377538627","https://openalex.org/W2107220315","https://openalex.org/W1589637664"],"abstract_inverted_index":{"Robust":[0,144],"Policy":[1,145],"Search":[2],"is":[3,23],"the":[4,35,49,68,73,117,123,141],"problem":[5,142],"of":[6,45,60,125,143],"learning":[7,80],"policies":[8,28],"that":[9,70],"do":[10],"not":[11],"degrade":[12],"in":[13,30,51,72,119],"performance":[14,124],"when":[15],"subject":[16],"to":[17,34,62,84,94,102,140,154],"unseen":[18],"environment":[19,33],"model":[20,87],"parameters.":[21],"It":[22],"particularly":[24],"relevant":[25],"for":[26,89],"transferring":[27],"learned":[29],"a":[31,105,136],"simulation":[32],"real":[36],"world.":[37],"Several":[38],"existing":[39,155],"approaches":[40],"involve":[41],"sampling":[42],"large":[43],"batches":[44],"trajectories":[46],"which":[47],"reflect":[48],"differences":[50],"various":[52],"possible":[53],"environments,":[54],"and":[55,114,122,147],"then":[56],"selecting":[57],"some":[58],"subset":[59],"these":[61],"learn":[63],"robust":[64],"policies,":[65],"such":[66,104],"as":[67,93,97,100],"ones":[69],"result":[71],"worst":[74],"performance.":[75],"We":[76,107,133],"propose":[77],"an":[78],"active":[79],"based":[81],"framework,":[82],"EffAcTS,":[83],"selectively":[85],"choose":[86],"parameters":[88],"this":[90,109],"purpose":[91],"so":[92],"collect":[95],"only":[96],"much":[98],"data":[99],"necessary":[101],"select":[103],"subset.":[106],"apply":[108],"framework":[110,153],"using":[111],"Linear":[112],"Bandits,":[113],"experimentally":[115],"validate":[116],"gains":[118],"sample":[120],"efficiency":[121],"our":[126,151],"approach":[127],"on":[128,157],"standard":[129],"continuous":[130],"control":[131],"tasks.":[132],"also":[134],"present":[135],"Multi-Task":[137,158],"Learning":[138],"perspective":[139],"Search,":[146],"draw":[148],"connections":[149],"from":[150],"proposed":[152],"work":[156],"Learning.":[159]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}