{"id":"https://openalex.org/W4415078270","doi":"https://doi.org/10.1007/978-3-032-08064-6_3","title":"Explore Reinforced: Equilibrium Approximation with\u00a0Reinforcement Learning","display_name":"Explore Reinforced: Equilibrium Approximation with\u00a0Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-11","ids":{"openalex":"https://openalex.org/W4415078270","doi":"https://doi.org/10.1007/978-3-032-08064-6_3"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-08064-6_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-08064-6_3","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5101362040","display_name":"Mateusz Nowak","orcid":"https://orcid.org/0009-0006-5197-4966"},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mateusz Nowak","raw_affiliation_strings":["Dartmouth College, Hanover, USA"],"raw_orcid":"https://orcid.org/0009-0006-5197-4966","affiliations":[{"raw_affiliation_string":"Dartmouth College, Hanover, USA","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115004766","display_name":"Qintong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qintong Xie","raw_affiliation_strings":["Dartmouth College, Hanover, USA"],"raw_orcid":"https://orcid.org/0009-0001-2287-5049","affiliations":[{"raw_affiliation_string":"Dartmouth College, Hanover, USA","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066615912","display_name":"Emma-Jayne Graham","orcid":"https://orcid.org/0009-0003-7882-0586"},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emma Graham","raw_affiliation_strings":["Dartmouth College, Hanover, USA"],"raw_orcid":"https://orcid.org/0009-0003-7882-0586","affiliations":[{"raw_affiliation_string":"Dartmouth College, Hanover, USA","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101286077","display_name":"Ryan Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryan Yu","raw_affiliation_strings":["Boston University, Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University, Boston, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Michelle Yilin Feng","orcid":"https://orcid.org/0009-0009-7053-0924"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michelle Yilin Feng","raw_affiliation_strings":["Boston University, Boston, USA"],"raw_orcid":"https://orcid.org/0009-0009-7053-0924","affiliations":[{"raw_affiliation_string":"Boston University, Boston, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119955891","display_name":"Roy Leibovitz","orcid":null},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roy Leibovitz","raw_affiliation_strings":["Dartmouth College, Hanover, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dartmouth College, Hanover, USA","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004171682","display_name":"Xavier F. Cadet","orcid":"https://orcid.org/0000-0002-8545-0371"},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xavier Cadet","raw_affiliation_strings":["Dartmouth College, Hanover, USA"],"raw_orcid":"https://orcid.org/0000-0002-8545-0371","affiliations":[{"raw_affiliation_string":"Dartmouth College, Hanover, USA","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103044811","display_name":"Sang Chin","orcid":"https://orcid.org/0000-0002-1913-4223"},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Chin","raw_affiliation_strings":["Dartmouth College, Hanover, USA"],"raw_orcid":"https://orcid.org/0000-0002-1913-4223","affiliations":[{"raw_affiliation_string":"Dartmouth College, Hanover, USA","institution_ids":["https://openalex.org/I107672454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101362040"],"corresponding_institution_ids":["https://openalex.org/I107672454"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64806809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9995999932289124,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9995999932289124,"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":0.9980999827384949,"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/T12288","display_name":"Optimization and Search Problems","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.755299985408783},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5975000262260437},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.5591999888420105},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4341000020503998},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.41760000586509705},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3781999945640564},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.3336000144481659}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807999849319458},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.755299985408783},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5975000262260437},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.5591999888420105},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5109000205993652},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3779999911785126},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C94766913","wikidata":"https://www.wikidata.org/wiki/Q1530271","display_name":"Equilibrium point","level":3,"score":0.32760000228881836},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3181999921798706},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C193386753","wikidata":"https://www.wikidata.org/wiki/Q1130396","display_name":"Approximations of \u03c0","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2993812969","wikidata":"https://www.wikidata.org/wiki/Q1530271","display_name":"Equilibrium solution","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C131157278","wikidata":"https://www.wikidata.org/wiki/Q51363","display_name":"Thermodynamic equilibrium","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-08064-6_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-08064-6_3","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1570963478","https://openalex.org/W2077902449","https://openalex.org/W2118929276","https://openalex.org/W2145339207","https://openalex.org/W2169359757","https://openalex.org/W2508573783","https://openalex.org/W2574978968","https://openalex.org/W2575705757","https://openalex.org/W2950929549","https://openalex.org/W2970077127","https://openalex.org/W2998555768","https://openalex.org/W3174818244","https://openalex.org/W4281553483","https://openalex.org/W4390738792","https://openalex.org/W4407729347","https://openalex.org/W4409348659"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-12T00:00:00"}
