{"id":"https://openalex.org/W4378438546","doi":"https://doi.org/10.1007/978-3-031-33377-4_29","title":"Constrained Portfolio Management Using Action Space Decomposition for\u00a0Reinforcement Learning","display_name":"Constrained Portfolio Management Using Action Space Decomposition for\u00a0Reinforcement Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4378438546","doi":"https://doi.org/10.1007/978-3-031-33377-4_29"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-33377-4_29","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-33377-4_29","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-33377-4_29.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-33377-4_29.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027236108","display_name":"David Winkel","orcid":"https://orcid.org/0000-0001-8829-0863"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I4403386549","display_name":"Munich Center for Machine Learning","ror":"https://ror.org/02nfy3535","country_code":null,"type":"education","lineage":["https://openalex.org/I4403386549","https://openalex.org/I62916508","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"David Winkel","raw_affiliation_strings":["LMU Munich, Munich, Germany","Munich Center for Machine Learning (MCML), Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8829-0863","affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"raw_affiliation_string":"Munich Center for Machine Learning (MCML), Munich, Germany","institution_ids":["https://openalex.org/I4403386549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041119315","display_name":"Niklas Strau\u00df","orcid":"https://orcid.org/0000-0002-8083-7323"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I4403386549","display_name":"Munich Center for Machine Learning","ror":"https://ror.org/02nfy3535","country_code":null,"type":"education","lineage":["https://openalex.org/I4403386549","https://openalex.org/I62916508","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Niklas Strau\u00df","raw_affiliation_strings":["LMU Munich, Munich, Germany","Munich Center for Machine Learning (MCML), Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8083-7323","affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"raw_affiliation_string":"Munich Center for Machine Learning (MCML), Munich, Germany","institution_ids":["https://openalex.org/I4403386549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003177894","display_name":"Matthias Schubert","orcid":"https://orcid.org/0000-0002-6566-6343"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I4403386549","display_name":"Munich Center for Machine Learning","ror":"https://ror.org/02nfy3535","country_code":null,"type":"education","lineage":["https://openalex.org/I4403386549","https://openalex.org/I62916508","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Schubert","raw_affiliation_strings":["LMU Munich, Munich, Germany","Munich Center for Machine Learning (MCML), Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6566-6343","affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"raw_affiliation_string":"Munich Center for Machine Learning (MCML), Munich, Germany","institution_ids":["https://openalex.org/I4403386549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066743613","display_name":"Yunpu Ma","orcid":"https://orcid.org/0000-0001-6112-8794"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I4403386549","display_name":"Munich Center for Machine Learning","ror":"https://ror.org/02nfy3535","country_code":null,"type":"education","lineage":["https://openalex.org/I4403386549","https://openalex.org/I62916508","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yunpu Ma","raw_affiliation_strings":["LMU Munich, Munich, Germany","Munich Center for Machine Learning (MCML), Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6112-8794","affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"raw_affiliation_string":"Munich Center for Machine Learning (MCML), Munich, Germany","institution_ids":["https://openalex.org/I4403386549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003335849","display_name":"Thomas Seidl","orcid":"https://orcid.org/0000-0002-4861-1412"},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I4403386549","display_name":"Munich Center for Machine Learning","ror":"https://ror.org/02nfy3535","country_code":null,"type":"education","lineage":["https://openalex.org/I4403386549","https://openalex.org/I62916508","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Seidl","raw_affiliation_strings":["LMU Munich, Munich, Germany","Munich Center for Machine Learning (MCML), Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4861-1412","affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"raw_affiliation_string":"Munich Center for Machine Learning (MCML), Munich, Germany","institution_ids":["https://openalex.org/I4403386549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027236108"],"corresponding_institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I4403386549","https://openalex.org/I8204097"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.4977,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62404372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"373","last_page":"385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9754999876022339,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7793233394622803},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7644457817077637},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6069694757461548},{"id":"https://openalex.org/keywords/portfolio-optimization","display_name":"Portfolio optimization","score":0.6067695021629333},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5709498524665833},{"id":"https://openalex.org/keywords/portfolio","display_name":"Portfolio","score":0.5591447353363037},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.5432923436164856},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.539198637008667},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5099927186965942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5031728148460388},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4825395941734314},{"id":"https://openalex.org/keywords/project-portfolio-management","display_name":"Project portfolio management","score":0.47508731484413147},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46245694160461426},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4172939956188202},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3960202932357788},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.25533315539360046},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.14325755834579468},{"id":"https://openalex.org/keywords/project-management","display_name":"Project management","score":0.11679145693778992},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09817004203796387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7793233394622803},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7644457817077637},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6069694757461548},{"id":"https://openalex.org/C202655437","wikidata":"https://www.wikidata.org/wiki/Q7231728","display_name":"Portfolio optimization","level":3,"score":0.6067695021629333},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5709498524665833},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.5591447353363037},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.5432923436164856},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.539198637008667},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5099927186965942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5031728148460388},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4825395941734314},{"id":"https://openalex.org/C74510933","wikidata":"https://www.wikidata.org/wiki/Q1936145","display_name":"Project portfolio management","level":3,"score":0.47508731484413147},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46245694160461426},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4172939956188202},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3960202932357788},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.25533315539360046},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.14325755834579468},{"id":"https://openalex.org/C15952604","wikidata":"https://www.wikidata.org/wiki/Q179012","display_name":"Project management","level":2,"score":0.11679145693778992},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09817004203796387},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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":1,"locations":[{"id":"doi:10.1007/978-3-031-33377-4_29","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-33377-4_29","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-33377-4_29.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-33377-4_29","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-33377-4_29","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-33377-4_29.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378438546.pdf"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W2073314543","https://openalex.org/W2575705757","https://openalex.org/W2758803042","https://openalex.org/W2769883686","https://openalex.org/W2980433389","https://openalex.org/W2998619042","https://openalex.org/W3200606641","https://openalex.org/W4285600796","https://openalex.org/W4360985603","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W2937181779","https://openalex.org/W2949964922","https://openalex.org/W1662842982","https://openalex.org/W4362598698","https://openalex.org/W2908009194","https://openalex.org/W2553738733","https://openalex.org/W4294612823","https://openalex.org/W2633862945","https://openalex.org/W2942916884","https://openalex.org/W2528567696"],"abstract_inverted_index":{"Abstract":[0],"Financial":[1],"portfolio":[2,21,95],"managers":[3],"typically":[4],"face":[5],"multi-period":[6],"optimization":[7],"tasks":[8],"such":[9],"as":[10],"short-selling":[11],"or":[12],"investing":[13],"at":[14],"least":[15],"a":[16,23,71],"particular":[17],"portion":[18],"of":[19,53],"the":[20,84],"in":[22],"specific":[24],"industry":[25],"sector.":[26],"A":[27],"common":[28],"approach":[29,104],"to":[30,35,79,83],"tackle":[31],"these":[32],"problems":[33],"is":[34],"use":[36],"constrained":[37],"Markov":[38],"decision":[39],"process":[40],"(CMDP)":[41],"methods,":[42],"which":[43],"may":[44],"suffer":[45],"from":[46],"sample":[47],"inefficiency,":[48],"hyperparameter":[49],"tuning,":[50],"and":[51],"lack":[52],"guarantees":[54],"for":[55,69,110],"constraint":[56],"violations.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61],"propose":[62],"Action":[63],"Space":[64],"Decomposition":[65],"Based":[66],"Optimization":[67],"(ADBO)":[68],"optimizing":[70],"more":[72],"straightforward":[73],"surrogate":[74],"task":[75],"that":[76,101],"allows":[77],"actions":[78],"be":[80],"mapped":[81],"back":[82],"original":[85],"task.":[86],"We":[87],"examine":[88],"our":[89,102],"method":[90],"on":[91],"two":[92],"real-world":[93],"data":[94],"construction":[96],"tasks.":[97],"The":[98],"results":[99],"show":[100],"new":[103],"consistently":[105],"outperforms":[106],"state-of-the-art":[107],"benchmark":[108],"approaches":[109],"general":[111],"CMDPs.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
