{"id":"https://openalex.org/W4416107873","doi":"https://doi.org/10.1145/3736425.3770113","title":"Ibex-RL: Interpretable and Scalable Control via Physics-Informed Reinforcement Learning","display_name":"Ibex-RL: Interpretable and Scalable Control via Physics-Informed Reinforcement Learning","publication_year":2025,"publication_date":"2025-11-11","ids":{"openalex":"https://openalex.org/W4416107873","doi":"https://doi.org/10.1145/3736425.3770113"},"language":null,"primary_location":{"id":"doi:10.1145/3736425.3770113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736425.3770113","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th 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":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3736425.3770113","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093192090","display_name":"Ozan Baris Mulayim","orcid":"https://orcid.org/0009-0004-5302-0352"},"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":true,"raw_author_name":"Ozan Baris Mulayim","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064458775","display_name":"Mario Berg\u00e9s","orcid":"https://orcid.org/0000-0003-2948-9236"},"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":"Mario Berg\u00e9s","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5093192090"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38191117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"192","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.2928999960422516,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.2928999960422516,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.13809999823570251,"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/T10603","display_name":"Smart Grid Energy Management","score":0.13650000095367432,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7634999752044678},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5773000121116638},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5250999927520752},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5231999754905701},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.32440000772476196},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3118000030517578},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.31119999289512634}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7634999752044678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307999730110168},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5773000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5633999705314636},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5231999754905701},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49869999289512634},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2621999979019165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3736425.3770113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736425.3770113","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3736425.3770113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736425.3770113","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W846474976","https://openalex.org/W1988382136","https://openalex.org/W2922286784","https://openalex.org/W3004359627","https://openalex.org/W3087355053","https://openalex.org/W3199775902","https://openalex.org/W3212810272","https://openalex.org/W4226494903","https://openalex.org/W4377101023","https://openalex.org/W4378571872","https://openalex.org/W4398162525","https://openalex.org/W4399916322","https://openalex.org/W4400275615","https://openalex.org/W4404036943","https://openalex.org/W4409293702","https://openalex.org/W4412651325"],"related_works":[],"abstract_inverted_index":{"While":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"offers":[4],"a":[5,18],"powerful":[6],"framework":[7],"for":[8],"optimizing":[9],"HVAC":[10],"systems,":[11],"its":[12],"practical":[13],"and":[14,45],"scalable":[15],"deployment":[16],"remains":[17],"significant":[19],"challenge.":[20],"Real-world":[21],"application":[22],"is":[23],"often":[24],"hindered":[25],"because":[26],"existing":[27],"RL":[28],"agents":[29],"typically":[30],"require":[31],"large":[32],"amounts":[33],"of":[34],"training":[35],"data,":[36],"operate":[37],"as":[38],"\"black-box\"":[39],"models":[40],"opaque":[41],"to":[42],"expert":[43],"interrogation,":[44],"rely":[46],"on":[47],"laborious":[48],"manual":[49],"reward":[50],"shaping.":[51]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-11T00:00:00"}