{"id":"https://openalex.org/W2967257869","doi":"https://doi.org/10.1109/icra.2019.8793650","title":"Adaptive Variance for Changing Sparse-Reward Environments","display_name":"Adaptive Variance for Changing Sparse-Reward Environments","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2967257869","doi":"https://doi.org/10.1109/icra.2019.8793650","mag":"2967257869"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8793650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8793650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103223385","display_name":"Xingyu Lin","orcid":"https://orcid.org/0000-0002-2454-2520"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingyu Lin","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040035146","display_name":"Pengsheng Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengsheng Guo","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001534200","display_name":"Carlos Florensa","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Florensa","raw_affiliation_strings":["EECS Department, UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS Department, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037048516","display_name":"David Held","orcid":"https://orcid.org/0000-0003-0537-1508"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Held","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"3210","last_page":"3216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9904999732971191,"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":0.9793000221252441,"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/variance","display_name":"Variance (accounting)","score":0.7891407012939453},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7495907545089722},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.7133450508117676},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6611095070838928},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6328715085983276},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5361241102218628},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5287313461303711},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4997904300689697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4870651066303253},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4823586344718933},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.44950568675994873},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.431968629360199},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3212655186653137},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21170839667320251},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13206464052200317},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09946224093437195}],"concepts":[{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.7891407012939453},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7495907545089722},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.7133450508117676},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6611095070838928},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6328715085983276},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5361241102218628},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5287313461303711},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4997904300689697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4870651066303253},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4823586344718933},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.44950568675994873},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.431968629360199},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3212655186653137},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21170839667320251},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13206464052200317},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09946224093437195},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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":1,"locations":[{"id":"doi:10.1109/icra.2019.8793650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8793650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W1493730910","https://openalex.org/W1522301498","https://openalex.org/W1585854823","https://openalex.org/W1587845729","https://openalex.org/W1771410628","https://openalex.org/W2005243481","https://openalex.org/W2009424996","https://openalex.org/W2010189695","https://openalex.org/W2024390895","https://openalex.org/W2080759927","https://openalex.org/W2115524942","https://openalex.org/W2119717200","https://openalex.org/W2129113961","https://openalex.org/W2158782408","https://openalex.org/W2161464185","https://openalex.org/W2162651021","https://openalex.org/W2167489871","https://openalex.org/W2280163991","https://openalex.org/W2356031020","https://openalex.org/W2462906003","https://openalex.org/W2514775068","https://openalex.org/W2561776174","https://openalex.org/W2578206533","https://openalex.org/W2593044849","https://openalex.org/W2593766708","https://openalex.org/W2594103415","https://openalex.org/W2604763608","https://openalex.org/W2610818722","https://openalex.org/W2736601468","https://openalex.org/W2755611049","https://openalex.org/W2762872434","https://openalex.org/W2767050701","https://openalex.org/W2949475445","https://openalex.org/W2949561945","https://openalex.org/W2951507724","https://openalex.org/W2963267001","https://openalex.org/W2963276097","https://openalex.org/W2963411833","https://openalex.org/W2963614114","https://openalex.org/W2963751259","https://openalex.org/W2963887494","https://openalex.org/W2963938771","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2964173023","https://openalex.org/W2990747716","https://openalex.org/W3101442004","https://openalex.org/W4234453731","https://openalex.org/W4244473079","https://openalex.org/W4246994868","https://openalex.org/W4285719527","https://openalex.org/W4297791094","https://openalex.org/W4297824641","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6683278628","https://openalex.org/W6692846177","https://openalex.org/W6695011786","https://openalex.org/W6706320068","https://openalex.org/W6713603661","https://openalex.org/W6717230150","https://openalex.org/W6718836005","https://openalex.org/W6726216181","https://openalex.org/W6728252718","https://openalex.org/W6730641667","https://openalex.org/W6731982132","https://openalex.org/W6734097942","https://openalex.org/W6734206676","https://openalex.org/W6734517396","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6744563498","https://openalex.org/W6770858630","https://openalex.org/W7062612498"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W4255576661","https://openalex.org/W1516574938","https://openalex.org/W1964286703","https://openalex.org/W2169866437"],"abstract_inverted_index":{"Robots":[0],"that":[1,69],"are":[2],"trained":[3],"to":[4,18,22,32,73,87],"perform":[5],"a":[6,9,23,29,64,90],"task":[7],"in":[8,39,89],"fixed":[10],"environment":[11,20],"often":[12],"fail":[13],"when":[14],"facing":[15],"unexpected":[16],"changes":[17,88],"the":[19,34,53,56,60,79,82],"due":[21],"lack":[24],"of":[25,81,92],"exploration.":[26],"We":[27],"propose":[28],"principled":[30],"way":[31],"adapt":[33,86],"policy":[35,66],"for":[36,63,77],"better":[37],"exploration":[38,62],"changing":[40],"sparse-reward":[41,93],"environments.":[42,94],"Unlike":[43],"previous":[44],"works":[45],"which":[46],"explicitly":[47],"model":[48],"environmental":[49],"changes,":[50],"we":[51],"analyze":[52],"relationship":[54],"between":[55],"value":[57],"function":[58],"and":[59,67],"optimal":[61],"Gaussian-parameterized":[65],"show":[68],"our":[70],"theory":[71],"leads":[72],"an":[74],"effective":[75],"strategy":[76],"adjusting":[78],"variance":[80],"policy,":[83],"enabling":[84],"fast":[85],"variety":[91]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}