{"id":"https://openalex.org/W3204843673","doi":"https://doi.org/10.1109/case49439.2021.9551472","title":"Survivable Robotic Control through Guided Bayesian Policy Search with Deep Reinforcement Learning","display_name":"Survivable Robotic Control through Guided Bayesian Policy Search with Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3204843673","doi":"https://doi.org/10.1109/case49439.2021.9551472","mag":"3204843673"},"language":"en","primary_location":{"id":"doi:10.1109/case49439.2021.9551472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case49439.2021.9551472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"type":"article","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/A5048669336","display_name":"Sayyed Jaffar Ali Raza","orcid":"https://orcid.org/0000-0002-0948-8263"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sayyed Jaffar Ali Raza","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057842142","display_name":"Apan Dastider","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Apan Dastider","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060908808","display_name":"Mingjie Lin","orcid":"https://orcid.org/0000-0002-3225-4406"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingjie Lin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Univ. of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Univ. of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048669336"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6379585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1188","last_page":"1193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9941999912261963,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9922000169754028,"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":0.7581804990768433},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7271143794059753},{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.654798150062561},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.632289469242096},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5438985228538513},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.543124794960022},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.47561556100845337},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4649324119091034},{"id":"https://openalex.org/keywords/physics-engine","display_name":"Physics engine","score":0.4577440619468689},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4306144714355469},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.2138155996799469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581804990768433},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7271143794059753},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.654798150062561},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.632289469242096},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5438985228538513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.543124794960022},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.47561556100845337},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4649324119091034},{"id":"https://openalex.org/C190390380","wikidata":"https://www.wikidata.org/wiki/Q62505","display_name":"Physics engine","level":2,"score":0.4577440619468689},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4306144714355469},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2138155996799469},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case49439.2021.9551472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case49439.2021.9551472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1495862233","https://openalex.org/W1738827650","https://openalex.org/W2121863487","https://openalex.org/W2164569010","https://openalex.org/W2950492145"],"related_works":["https://openalex.org/W2083200807","https://openalex.org/W2154523322","https://openalex.org/W2364195017","https://openalex.org/W2049983405","https://openalex.org/W2355430452","https://openalex.org/W1603137082","https://openalex.org/W2392315374","https://openalex.org/W1951195060","https://openalex.org/W2092787235","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Many":[0],"robot":[1,180],"manipulation":[2,34,84],"skills":[3],"can":[4,215],"be":[5,50,216],"represented":[6],"with":[7,85],"deterministic":[8],"characteristics":[9],"and":[10,81,126,187,201],"there":[11],"exist":[12],"efficient":[13],"techniques":[14],"for":[15,20],"learning":[16,173],"parameterized":[17],"motor":[18],"plans":[19],"those":[21],"skills.":[22],"However,":[23],"one":[24],"of":[25,38,78,88,123,147,198,212],"the":[26],"active":[27],"research":[28],"challenge":[29],"still":[30],"remains":[31],"to":[32,52,59,73,101,129],"sustain":[33],"capabilities":[35],"in":[36,75,110,114,121,196,205],"situation":[37,77],"a":[39,46,67,76,178],"mechanical":[40,79],"failure.":[41],"Ideally,":[42],"like":[43],"biological":[44],"creatures,":[45],"robotic":[47],"agent":[48,72],"should":[49],"able":[51],"reconfigure":[53],"its":[54],"control":[55],"policy":[56,104,118,133,138],"by":[57,106,155],"adapting":[58],"dynamic":[60],"adversaries.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"propose":[66],"method":[68,92,168,193],"that":[69,191],"allows":[70,144],"an":[71],"survive":[74],"loss,":[80],"adaptively":[82],"learn":[83],"compromised":[86],"degrees":[87],"freedom-we":[89],"call":[90],"our":[91,166,188,192,213],"Survivable":[93],"Robotic":[94],"Learning":[95],"(SRL).":[96],"Our":[97],"key":[98],"idea":[99],"is":[100,153],"leverage":[102],"Bayesian":[103],"gradient":[105,152],"encoding":[107],"knowledge":[108],"bias":[109,158],"posterior":[111,149],"estimation,":[112],"which":[113,143,182],"turn":[115],"alleviates":[116],"future":[117],"search":[119,134],"explorations,":[120],"terms":[122,197],"sample":[124,199],"efficiency":[125],"when":[127],"compared":[128],"random":[130],"exploration":[131],"based":[132],"methods.":[135],"SRL":[136],"represents":[137],"priors":[139],"as":[140,159],"Gaussian":[141],"process,":[142],"tractable":[145],"computation":[146],"approximate":[148],"(when":[150],"true":[151],"intractable),":[154],"incorporating":[156],"guided":[157],"proxy":[160],"from":[161],"prior":[162],"replays.":[163],"We":[164],"evaluate":[165],"proposed":[167],"against":[169],"off-the-shelf":[170],"model":[171],"free":[172],"algorithm":[174],"(DDPG),":[175],"testing":[176],"on":[177],"hexapod":[179],"platform":[181],"encounters":[183],"incremental":[184],"failure":[185,207],"emulation,":[186],"experiments":[189,214],"show":[190],"improves":[194],"largely":[195],"requirement":[200],"quantitative":[202],"success":[203],"ratio":[204],"all":[206],"modes.":[208],"A":[209],"demonstration":[210],"video":[211],"viewed":[217],"at:":[218],"https://sites.google.com/view/survivalrl":[219]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}