{"id":"https://openalex.org/W7204259557","doi":"https://doi.org/10.18280/isi.310728","title":"A Cooperative Multi-Agent Reinforcement Learning Framework for Two-Echelon Inventory Control with Behavioral Cloning and Monotonicity Constraints","display_name":"A Cooperative Multi-Agent Reinforcement Learning Framework for Two-Echelon Inventory Control with Behavioral Cloning and Monotonicity Constraints","publication_year":2026,"publication_date":"2026-07-31","ids":{"openalex":"https://openalex.org/W7204259557","doi":"https://doi.org/10.18280/isi.310728"},"language":"en","primary_location":{"id":"doi:10.18280/isi.310728","doi":"https://doi.org/10.18280/isi.310728","is_oa":true,"landing_page_url":"https://doi.org/10.18280/isi.310728","pdf_url":null,"source":{"id":"https://openalex.org/S1757003","display_name":"Ing\u00e9nierie des syst\u00e8mes d information","issn_l":"1633-1311","issn":["1633-1311","2116-7125"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310311056","host_organization_name":"Lavoisier publishing","host_organization_lineage":["https://openalex.org/P4310311056"],"host_organization_lineage_names":["Lavoisier publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ing\u00e9nierie des syst\u00e8mes d information","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.18280/isi.310728","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016714566","display_name":"Kunj Modi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kunj Modi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148293748","display_name":"Hitansh Mehta","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hitansh Mehta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014281714","display_name":"Vidit Thakkar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vidit Thakkar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091211898","display_name":"Darshana Sankhe","orcid":"https://orcid.org/0000-0001-8510-5810","observed_orcids":["https://orcid.org/0000-0001-8510-5810"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Darshana Sankhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120168318","display_name":"Paresh Nasikkar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paresh Nasikkar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143666102","display_name":"Ankita Gupta","orcid":"https://orcid.org/0009-0001-9995-0043","observed_orcids":["https://orcid.org/0009-0001-9995-0043"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankita Gupta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148394632","display_name":"Deepali Patil","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deepali Patil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068585632","display_name":"Pratik Kanani","orcid":"https://orcid.org/0000-0002-6848-2507","observed_orcids":["https://orcid.org/0000-0002-6848-2507","https://orcid.org/0000-0002-6918-4632"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pratik Kanani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":"7","first_page":"2477","last_page":"2487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9613999724388123,"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"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9613999724388123,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.03550000116229057,"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/T11814","display_name":"Advanced Manufacturing and Logistics Optimization","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.8690000176429749},{"id":"https://openalex.org/keywords/collaborative-learning","display_name":"cooperative learning","score":0.5220000147819519},{"id":"https://openalex.org/keywords/behavioral-cloning","display_name":"behavior cloning","score":0.9380000233650208},{"id":"https://openalex.org/keywords/monotonicity-constraints","display_name":"monotonicity constraints","score":0.9869999885559082},{"id":"https://openalex.org/keywords/inventory-management","display_name":"inventory management","score":0.5839999914169312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5695000290870667},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5691999793052673},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44620001316070557},{"id":"https://openalex.org/C117938511","wikidata":"https://www.wikidata.org/wiki/Q3634830","display_name":"Inventory control","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3433000147342682},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.26660001277923584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18280/isi.310728","doi":"https://doi.org/10.18280/isi.310728","is_oa":true,"landing_page_url":"https://doi.org/10.18280/isi.310728","pdf_url":null,"source":{"id":"https://openalex.org/S1757003","display_name":"Ing\u00e9nierie des syst\u00e8mes d information","issn_l":"1633-1311","issn":["1633-1311","2116-7125"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310311056","host_organization_name":"Lavoisier publishing","host_organization_lineage":["https://openalex.org/P4310311056"],"host_organization_lineage_names":["Lavoisier publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ing\u00e9nierie des syst\u00e8mes d information","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.18280/isi.310728","doi":"https://doi.org/10.18280/isi.310728","is_oa":true,"landing_page_url":"https://doi.org/10.18280/isi.310728","pdf_url":null,"source":{"id":"https://openalex.org/S1757003","display_name":"Ing\u00e9nierie des syst\u00e8mes d information","issn_l":"1633-1311","issn":["1633-1311","2116-7125"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310311056","host_organization_name":"Lavoisier publishing","host_organization_lineage":["https://openalex.org/P4310311056"],"host_organization_lineage_names":["Lavoisier publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ing\u00e9nierie des syst\u00e8mes d information","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7222945551","https://openalex.org/W2283333707","https://openalex.org/W2291763734","https://openalex.org/W2256686932","https://openalex.org/W7145053725","https://openalex.org/W4400582838","https://openalex.org/W2152974163","https://openalex.org/W7133230201","https://openalex.org/W7169797263","https://openalex.org/W7220705224"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-27T00:00:00"}
