{"id":"https://openalex.org/W3200083785","doi":"https://doi.org/10.1613/jair.1.13350","title":"Jointly Learning Environments and Control Policies with Projected Stochastic Gradient Ascent","display_name":"Jointly Learning Environments and Control Policies with Projected Stochastic Gradient Ascent","publication_year":2022,"publication_date":"2022-01-05","ids":{"openalex":"https://openalex.org/W3200083785","doi":"https://doi.org/10.1613/jair.1.13350","mag":"3200083785"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.13350","pdf_url":"https://jair.org/index.php/jair/article/download/13350/26757","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://jair.org/index.php/jair/article/download/13350/26757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075103449","display_name":"Adrien Bolland","orcid":null},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Adrien Bolland","raw_affiliation_strings":["Montefiore Institute University of Li\u00e8ge Li\u00e8ge, Belgium"],"affiliations":[{"raw_affiliation_string":"Montefiore Institute University of Li\u00e8ge Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060317028","display_name":"Ioannis Boukas","orcid":"https://orcid.org/0000-0002-0109-9896"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ioannis Boukas","raw_affiliation_strings":["Montefiore Institute University of Li\u00e8ge Li\u00e8ge, Belgium"],"affiliations":[{"raw_affiliation_string":"Montefiore Institute University of Li\u00e8ge Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090854304","display_name":"Mathias Berger","orcid":"https://orcid.org/0000-0003-3081-4833"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Mathias Berger","raw_affiliation_strings":["Montefiore Institute University of Li\u00e8ge Li\u00e8ge, Belgium"],"affiliations":[{"raw_affiliation_string":"Montefiore Institute University of Li\u00e8ge Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077011518","display_name":"Damien Ernst","orcid":"https://orcid.org/0000-0002-3035-8260"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Damien Ernst","raw_affiliation_strings":["Montefiore Institute University of Li\u00e8ge Li\u00e8ge, Belgium"],"affiliations":[{"raw_affiliation_string":"Montefiore Institute University of Li\u00e8ge Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":0,"currency":"USD","value_usd":0,"provenance":"doaj"},"apc_paid":null,"fwci":0.486,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":3,"citation_normalized_percentile":{"value":0.99997,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":76,"max":80},"biblio":{"volume":"73","issue":null,"first_page":"117","last_page":"171"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977,"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":0.9977,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.9865,"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/T12617","display_name":"Energy, Environment, and Transportation Policies","score":0.984,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.44897926}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7862225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6992869},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6385463},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5246525},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.44897926},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4271524},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24947116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2142536},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1811513},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.13350","pdf_url":"https://jair.org/index.php/jair/article/download/13350/26757","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/247965","pdf_url":"https://orbi.uliege.be/bitstream/2268/247965/1/DEPS.pdf","source":{"id":"https://openalex.org/S4306401300","display_name":"ORBi (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":["University of Li\u00e8ge"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2006.01738","pdf_url":"https://arxiv.org/pdf/2006.01738","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.13350","pdf_url":"https://jair.org/index.php/jair/article/download/13350/26757","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":64,"referenced_works":["https://openalex.org/W106556187","https://openalex.org/W114517082","https://openalex.org/W1505731132","https://openalex.org/W1522301498","https://openalex.org/W1533927702","https://openalex.org/W1569990960","https://openalex.org/W1754068669","https://openalex.org/W1771410628","https://openalex.org/W1806891645","https://openalex.org/W2008150460","https://openalex.org/W2030328066","https://openalex.org/W2046376809","https://openalex.org/W2082931571","https://openalex.org/W2085966040","https://openalex.org/W2098432798","https://openalex.org/W2101677491","https://openalex.org/W2107726111","https://openalex.org/W2108051346","https://openalex.org/W2119717200","https://openalex.org/W2133196698","https://openalex.org/W2152482851","https://openalex.org/W2161149069","https://openalex.org/W2163969905","https://openalex.org/W2175161357","https://openalex.org/W2311756909","https://openalex.org/W2321739562","https://openalex.org/W2395756713","https://openalex.org/W2615070957","https://openalex.org/W2736021157","https://openalex.org/W2736601468","https://openalex.org/W2746747028","https://openalex.org/W2774386693","https://openalex.org/W2781726626","https://openalex.org/W2790935339","https://openalex.org/W2920966515","https://openalex.org/W2937555108","https://openalex.org/W2951815432","https://openalex.org/W2962696179","https://openalex.org/W2963030777","https://openalex.org/W2964043796","https://openalex.org/W3003294786","https://openalex.org/W3035700320","https://openalex.org/W3036766693","https://openalex.org/W3038822267","https://openalex.org/W3043995598","https://openalex.org/W3048943668","https://openalex.org/W3097575142","https://openalex.org/W3102923851","https://openalex.org/W3106462682","https://openalex.org/W3106528330","https://openalex.org/W3109497027","https://openalex.org/W3148904829","https://openalex.org/W3162373567","https://openalex.org/W3179456407","https://openalex.org/W4200413037","https://openalex.org/W4230563027","https://openalex.org/W4234117503","https://openalex.org/W4287690684","https://openalex.org/W4288375398","https://openalex.org/W4292510839","https://openalex.org/W4297825603","https://openalex.org/W4301435544","https://openalex.org/W4321150118","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W4380318855","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W3049728571","https://openalex.org/W2586732548","https://openalex.org/W2138720691","https://openalex.org/W20361778","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W1644951908"],"abstract_inverted_index":{"We":[0,17,73,137,187],"consider":[1],"the":[2,19,41,48,55,59,99,102,118,139,149,236],"joint":[3,182,245],"design":[4,33,150,183],"and":[5,34,58,66,108,111,122,133,151,162,184,232],"control":[6,36,152,185],"of":[7,44,101,120,141,153],"discrete-time":[8],"stochastic":[9],"dynamical":[10],"systems":[11],"over":[12,47],"a":[13,22,31,35,76,154,157,163,173],"finite":[14],"time":[15,49],"horizon.":[16],"formulate":[18],"problem":[20,25],"as":[21,130,194],"multi-step":[23],"optimization":[24,87,246],"under":[26],"uncertainty":[27],"seeking":[28],"to":[29,70,89,129,180],"identify":[30],"system":[32,161],"policy":[37,60,82,123,233],"that":[38,189,226,238],"jointly":[39,229],"maximize":[40],"expected":[42,103],"sum":[43],"rewards":[45],"collected":[46],"horizon":[50],"considered.":[51],"The":[52],"transition":[53],"function,":[54],"reward":[56],"function":[57],"are":[61,217],"all":[62,199],"parametrized,":[63],"assumed":[64],"known":[65],"differentiable":[67],"with":[68,85,148,205,220],"respect":[69],"their":[71],"parameters.":[72,124],"then":[74],"introduce":[75],"deep":[77,175],"reinforcement":[78,176],"learning":[79,177],"algorithm":[80,96,126,143,169,178,216,225],"combining":[81],"gradient":[83,100,114],"methods":[84],"model-based":[86],"techniques":[88],"solve":[90],"this":[91],"problem.":[92],"In":[93,166],"essence,":[94],"our":[95,142,168,215],"iteratively":[97],"approximates":[98],"return":[104],"via":[105],"Monte-Carlo":[106],"sampling":[107],"automatic":[109],"differentiation":[110],"takes":[112],"projected":[113],"ascent":[115],"steps":[116],"in":[117,144,198,208],"space":[119],"environment":[121,231],"This":[125],"is":[127,170,247],"referred":[128],"Direct":[131],"Environment":[132],"Policy":[134],"Search":[135],"(DEPS).":[136],"assess":[138],"performance":[140],"three":[145,200],"environments":[146],"concerned":[147],"mass-spring-damper":[155],"system,":[156],"small-scale":[158],"off-grid":[159],"power":[160],"drone,":[164],"respectively.":[165],"addition,":[167],"benchmarked":[171],"against":[172],"state-of-the-art":[174],"used":[179],"tackle":[181],"problems.":[186],"show":[188],"DEPS":[190],"performs":[191],"at":[192],"least":[193],"well":[195],"or":[196],"better":[197],"environments,":[201],"consistently":[202],"yielding":[203],"solutions":[204,212,221],"higher":[206,239],"returns":[207,240],"fewer":[209],"iterations.":[210],"Finally,":[211],"produced":[213,222],"by":[214,223],"also":[218],"compared":[219],"an":[224],"does":[227],"not":[228],"optimize":[230],"parameters,":[234],"highlighting":[235],"fact":[237],"can":[241],"be":[242],"achieved":[243],"when":[244],"performed.":[248]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3200083785","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2024-12-07T14:57:39.519626","created_date":"2021-09-27"}