{"id":"https://openalex.org/W4310881482","doi":"https://doi.org/10.1145/3563357.3564055","title":"Constrained differentiable cross-entropy method for safe model-based reinforcement learning","display_name":"Constrained differentiable cross-entropy method for safe model-based reinforcement learning","publication_year":2022,"publication_date":"2022-11-09","ids":{"openalex":"https://openalex.org/W4310881482","doi":"https://doi.org/10.1145/3563357.3564055"},"language":"en","primary_location":{"id":"doi:10.1145/3563357.3564055","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3563357.3564055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","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/A5024609448","display_name":"Sam Mottahedi","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sam Mottahedi","raw_affiliation_strings":["The Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086068938","display_name":"Gregory S. Pavlak","orcid":"https://orcid.org/0000-0003-4734-0750"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory S. Pavlak","raw_affiliation_strings":["The Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024609448"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54236877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9901000261306763,"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":0.9901000261306763,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9883000254631042,"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/T11954","display_name":"Energy Efficiency and Management","score":0.9807000160217285,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9042013883590698},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.7698036432266235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6941664218902588},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5473430752754211},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5285769104957581},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4924057722091675},{"id":"https://openalex.org/keywords/cross-entropy-method","display_name":"Cross-entropy method","score":0.48994582891464233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4297507107257843},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32414472103118896},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.3196326196193695},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24043968319892883},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1523784101009369}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9042013883590698},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.7698036432266235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6941664218902588},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5473430752754211},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5285769104957581},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4924057722091675},{"id":"https://openalex.org/C75782508","wikidata":"https://www.wikidata.org/wiki/Q3333633","display_name":"Cross-entropy method","level":4,"score":0.48994582891464233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4297507107257843},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32414472103118896},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3196326196193695},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24043968319892883},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1523784101009369},{"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/C98036226","wikidata":"https://www.wikidata.org/wiki/Q7268356","display_name":"Quadratic assignment problem","level":3,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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:10.1145/3563357.3564055","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3563357.3564055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1965878388","https://openalex.org/W1990437501","https://openalex.org/W2018705428","https://openalex.org/W2054226461","https://openalex.org/W2130178506","https://openalex.org/W2133632477","https://openalex.org/W2134491302","https://openalex.org/W2155511972","https://openalex.org/W2182977695","https://openalex.org/W2605102758","https://openalex.org/W2625874945","https://openalex.org/W2822752092","https://openalex.org/W2902257695","https://openalex.org/W2913756371","https://openalex.org/W2985363569","https://openalex.org/W3003931103","https://openalex.org/W3049652862","https://openalex.org/W3109235893","https://openalex.org/W4206497039","https://openalex.org/W4283397781","https://openalex.org/W4299828299","https://openalex.org/W4388156124"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2348722996","https://openalex.org/W2334570605","https://openalex.org/W2474680198","https://openalex.org/W2054925885","https://openalex.org/W2049828308","https://openalex.org/W4255006213","https://openalex.org/W1998683226","https://openalex.org/W2597689725"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,34],"agents":[2,36,56],"must":[3],"explore":[4,82],"their":[5],"environments":[6,129],"to":[7,16,75,160],"learn":[8],"optimal":[9],"policies":[10],"through":[11],"trial":[12],"and":[13,81,130,155],"error.":[14],"Due":[15],"challenges":[17],"in":[18,38,47,58,118,126,143],"simulating":[19],"the":[20,23,39,59,73,79,110,114,149],"complexities":[21],"of":[22,31,43,152],"real":[24,40,60],"world,":[25],"there":[26],"is":[27],"a":[28,66,92,99,105,132],"growing":[29],"trend":[30],"training":[32,54],"reinforcement":[33,68],"(RL)":[35,70],"directly":[37,57],"world":[41],"instead":[42],"mostly":[44],"or":[45],"entirely":[46],"simulation.":[48],"Safety":[49,127],"concerns":[50],"are":[51],"paramount":[52],"when":[53],"RL":[55,120,163],"world.":[61],"This":[62],"paper":[63],"proposes":[64],"MPC-CDCEM,":[65],"model-based":[67,119],"algorithm":[69,90,125],"that":[71,108,142],"allows":[72],"agent":[74],"safely":[76],"interact":[77],"with":[78,98],"environment":[80],"without":[83],"additional":[84],"assumptions":[85],"on":[86,131],"system":[87],"dynamics.":[88],"The":[89],"uses":[91],"Model":[93],"Predictive":[94],"Control":[95],"(MPC)":[96],"framework":[97],"differentiable":[100,106],"cross-entropy":[101],"optimizer,":[102],"which":[103],"induces":[104],"policy":[107],"considers":[109],"constraints":[111],"while":[112],"addressing":[113],"objective":[115],"mismatch":[116],"problem":[117],"algorithms.":[121,164],"We":[122],"evaluate":[123],"our":[124,146],"Gym":[128],"practical":[133],"building":[134],"energy":[135],"optimization":[136],"problem.":[137],"In":[138],"addition,":[139],"we":[140],"showed":[141],"both":[144],"experiments,":[145],"algorithms":[147],"have":[148],"lowest":[150],"number":[151],"constraint":[153],"violations":[154],"achieve":[156],"comparable":[157],"rewards":[158],"compared":[159],"baseline":[161],"constrained":[162]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}