{"id":"https://openalex.org/W4412183830","doi":"https://doi.org/10.1007/s00521-025-11304-4","title":"GPI-tree search: algorithms for decision-time planning with the general policy improvement theorem","display_name":"GPI-tree search: algorithms for decision-time planning with the general policy improvement theorem","publication_year":2025,"publication_date":"2025-07-11","ids":{"openalex":"https://openalex.org/W4412183830","doi":"https://doi.org/10.1007/s00521-025-11304-4"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-025-11304-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11304-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11304-4.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11304-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057955697","display_name":"Louis Bagot","orcid":"https://orcid.org/0000-0001-6300-6993"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Louis Bagot","raw_affiliation_strings":["IDLab - Department of Computer Science, University of Antwerp - imec, The Beacon, Sint-Pietersvliet 7, 2000, Antwerp, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-6300-6993","affiliations":[{"raw_affiliation_string":"IDLab - Department of Computer Science, University of Antwerp - imec, The Beacon, Sint-Pietersvliet 7, 2000, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043305270","display_name":"Lynn D\u2019eer","orcid":"https://orcid.org/0000-0002-9358-8565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lynn D\u2019eer","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9358-8565","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Steven Latr\u00e9","orcid":"https://orcid.org/0000-0002-8267-9955"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Steven Latr\u00e9","raw_affiliation_strings":["IDLab - Department of Computer Science, University of Antwerp - imec, The Beacon, Sint-Pietersvliet 7, 2000, Antwerp, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-8267-9955","affiliations":[{"raw_affiliation_string":"IDLab - Department of Computer Science, University of Antwerp - imec, The Beacon, Sint-Pietersvliet 7, 2000, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006262997","display_name":"Tom De Schepper","orcid":"https://orcid.org/0000-0002-2969-3133"},"institutions":[{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tom De Schepper","raw_affiliation_strings":["Imec, Kapeldreef 75, Leuven, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-2969-3133","affiliations":[{"raw_affiliation_string":"Imec, Kapeldreef 75, Leuven, Belgium","institution_ids":["https://openalex.org/I4210114974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084961388","display_name":"Kevin Mets","orcid":"https://orcid.org/0000-0002-4812-4841"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kevin Mets","raw_affiliation_strings":["IDLab - Department of Electronics and Information and Communication Technology, Faculty of Applied Engineering, University of Antwerp - imec, The Beacon, Sint-Pietersvliet 7, 2000, Antwerp, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-4812-4841","affiliations":[{"raw_affiliation_string":"IDLab - Department of Electronics and Information and Communication Technology, Faculty of Applied Engineering, University of Antwerp - imec, The Beacon, Sint-Pietersvliet 7, 2000, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057955697"],"corresponding_institution_ids":["https://openalex.org/I149213910"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":2.0951,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88992246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"37","issue":"23","first_page":"18989","last_page":"19007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9965000152587891,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.987500011920929,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.7682694792747498},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5609193444252014},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5600157976150513},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4870050549507141},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46550920605659485},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3496057987213135},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31974688172340393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2865469455718994},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2862510681152344},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.18382331728935242}],"concepts":[{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.7682694792747498},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5609193444252014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5600157976150513},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4870050549507141},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46550920605659485},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3496057987213135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31974688172340393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2865469455718994},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2862510681152344},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.18382331728935242}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-025-11304-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11304-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11304-4.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-025-11304-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11304-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11304-4.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G3822991455","display_name":null,"funder_award_id":"101070596","funder_id":"https://openalex.org/F4320337994","funder_display_name":"HORIZON EUROPE Global Challenges and European Industrial Competitiveness"}],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null},{"id":"https://openalex.org/F4320335809","display_name":"Departement Economie, Wetenschap en Innovatie","ror":null},{"id":"https://openalex.org/F4320337994","display_name":"HORIZON EUROPE Global Challenges and European Industrial Competitiveness","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412183830.pdf","grobid_xml":"https://content.openalex.org/works/W4412183830.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1714211023","https://openalex.org/W1977989560","https://openalex.org/W1980035368","https://openalex.org/W1981276685","https://openalex.org/W1997840820","https://openalex.org/W2000080679","https://openalex.org/W2036803464","https://openalex.org/W2100677568","https://openalex.org/W2109910161","https://openalex.org/W2158782408","https://openalex.org/W2765689447","https://openalex.org/W2902907165","https://openalex.org/W2989847975","https://openalex.org/W2997123841","https://openalex.org/W3118210634","https://openalex.org/W4212996499","https://openalex.org/W4386484398","https://openalex.org/W6636592841"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W4409439182","https://openalex.org/W4393232657","https://openalex.org/W2053286651","https://openalex.org/W4412093237","https://openalex.org/W4410929354","https://openalex.org/W4390638272","https://openalex.org/W2181743346","https://openalex.org/W2187401768"],"abstract_inverted_index":{"In":[0,78],"Reinforcement":[1],"Learning,":[2],"Unsupervised":[3],"Skill":[4],"Discovery":[5],"tackles":[6],"the":[7,21,51,60,69,104,141,147,154,164,172,179,191],"learning":[8],"of":[9,23,124,146,194],"several":[10],"policies":[11,174],"for":[12,117,163],"downstream":[13],"task":[14],"transfer.":[15],"Once":[16],"these":[17],"skills":[18,70,142],"are":[19,175],"learnt,":[20],"question":[22],"how":[24],"best":[25],"to":[26,65,74,83,90,129,150],"use":[27,130],"and":[28,67,95,107,120,143,152],"combine":[29,68],"them":[30],"remains":[31],"an":[32],"open":[33],"problem.":[34],"The":[35],"General":[36],"Policy":[37],"Improvement":[38],"Theorem":[39],"(GPI)":[40],"creates":[41],"a":[42,85,99,122],"policy":[43,62,106,181],"stronger":[44,76,177],"than":[45,178],"any":[46,108],"individual":[47],"skill":[48],"by":[49],"selecting":[50],"highest-valued":[52],"policy,":[53],"generally":[54],"evaluated":[55],"with":[56,136,160],"Successor":[57,195],"Features.":[58,196],"However,":[59],"GPI":[61,105,148,180],"is":[63],"unable":[64],"mix":[66],"at":[71],"decision":[72],"time":[73],"formulate":[75],"plans.":[77],"this":[79],"paper,":[80],"we":[81,157],"propose":[82],"adopt":[84],"model-based":[86],"setting":[87],"in":[88],"order":[89],"make":[91],"such":[92],"planning":[93],"possible,":[94],"formally":[96],"show":[97,170],"that":[98,171],"forward":[100],"search":[101],"improves":[102],"on":[103],"shallower":[109],"searches":[110],"under":[111,184],"some":[112],"approximation":[113],"term.":[114],"We":[115],"argue":[116],"decision-time":[118],"planning,":[119],"design":[121,166],"family":[123],"algorithms,":[125],"GPI-Tree":[126],"Search":[127,134],"Algorithms,":[128],"Monte":[131],"Carlo":[132],"Tree":[133],"(MCTS)":[135],"GPI.":[137],"These":[138],"algorithms":[139],"foster":[140],"Q-value":[144],"priors":[145],"framework":[149],"guide":[151],"improve":[153,189],"search,":[155],"which":[156],"back":[158],"up":[159],"visual":[161],"intuition":[162],"different":[165],"choices.":[167],"Our":[168],"experiments":[169],"resulting":[173],"much":[176],"alone,":[182],"even":[183],"approximation;":[185],"they":[186],"can":[187],"also":[188],"beyond":[190],"linear":[192],"constraint":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}