{"id":"https://openalex.org/W1972683690","doi":"https://doi.org/10.1109/adprl.2013.6614993","title":"Optimized look-ahead trees: Extensions to large and continuous action spaces","display_name":"Optimized look-ahead trees: Extensions to large and continuous action spaces","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W1972683690","doi":"https://doi.org/10.1109/adprl.2013.6614993","mag":"1972683690"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2013.6614993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6614993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/handle/123456789/392672","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050771291","display_name":"Tobias Jung","orcid":"https://orcid.org/0000-0002-9159-8444"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Tobias Jung","raw_affiliation_strings":["Institut Montefiore, University of Li\u00e8ge, Belgium","Inst. Montefiore, Univ. of Liege, Lie\u0300ge, Belgium"],"affiliations":[{"raw_affiliation_string":"Institut Montefiore, University of Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]},{"raw_affiliation_string":"Inst. Montefiore, Univ. of Liege, Lie\u0300ge, Belgium","institution_ids":["https://openalex.org/I157674565"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077011518","display_name":"Damien Ernst","orcid":"https://orcid.org/0000-0002-3035-8260"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Damien Ernst","raw_affiliation_strings":["Institut Montefiore, University of Li\u00e8ge, Belgium","Inst. Montefiore, Univ. of Liege, Lie\u0300ge, Belgium"],"affiliations":[{"raw_affiliation_string":"Institut Montefiore, University of Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]},{"raw_affiliation_string":"Inst. Montefiore, Univ. of Liege, Lie\u0300ge, Belgium","institution_ids":["https://openalex.org/I157674565"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035651557","display_name":"Frederik Maes","orcid":"https://orcid.org/0000-0003-0027-1479"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Francis Maes","raw_affiliation_strings":["Department of Computer Science, Katholieke Universiteit, Leuven, Belgium","Dept. of Comput. Sci., Katholieke Univ. Leuven, Leuven, Belgium#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Katholieke Universiteit, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Katholieke Univ. Leuven, Leuven, Belgium#TAB#","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050771291"],"corresponding_institution_ids":["https://openalex.org/I157674565"],"apc_list":null,"apc_paid":null,"fwci":0.4266,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68422148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"12","issue":null,"first_page":"85","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9987000226974487,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/computer-science","display_name":"Computer science","score":0.7456551194190979},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6740232110023499},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5578801035881042},{"id":"https://openalex.org/keywords/look-ahead","display_name":"Look-ahead","score":0.5568509697914124},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5475162863731384},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.43559834361076355},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3355628252029419},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3315626382827759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28169095516204834},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15540117025375366},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1271604597568512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7456551194190979},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6740232110023499},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5578801035881042},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.5568509697914124},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5475162863731384},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.43559834361076355},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3355628252029419},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3315626382827759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28169095516204834},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15540117025375366},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1271604597568512},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/adprl.2013.6614993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6614993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/392672","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/392672","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Singapore, 16-19 April 2013","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:orbi.ulg.ac.be:2268/142357","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/142357","pdf_url":"https://orbi.uliege.be/bitstream/2268/142357/1/adprl13_web.pdf","source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc. of IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL'13) (2013); IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL'13), from 16-04-2013 to 19-04-2013","raw_type":"peer reviewed"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/392672","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/392672","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Singapore, 16-19 April 2013","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W871871845","https://openalex.org/W1540821927","https://openalex.org/W1625390266","https://openalex.org/W1783718104","https://openalex.org/W1969483458","https://openalex.org/W2016211524","https://openalex.org/W2096018174","https://openalex.org/W2097451572","https://openalex.org/W2120090487","https://openalex.org/W2158118484","https://openalex.org/W2159103845","https://openalex.org/W6623639079","https://openalex.org/W6632480443","https://openalex.org/W6678102440"],"related_works":["https://openalex.org/W4212766866","https://openalex.org/W1516515586","https://openalex.org/W1588099523","https://openalex.org/W2414184086","https://openalex.org/W204709730","https://openalex.org/W2962587647","https://openalex.org/W2084487854","https://openalex.org/W4241519009","https://openalex.org/W2353878298","https://openalex.org/W40494022"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"look-ahead":[3,36,52],"tree":[4,37],"based":[5],"control":[6,93],"policies":[7],"from":[8],"the":[9,18,30,49,57,80,86,104,113],"viewpoint":[10],"of":[11,27,44,51,59,79],"online":[12,64,73,114],"decision":[13,23],"making":[14],"with":[15,56,95],"constraints":[16],"on":[17,85,103],"computational":[19],"budget":[20],"allowed":[21],"per":[22],"(expressed":[24],"as":[25],"number":[26],"calls":[28],"to":[29,110],"generative":[31],"model).":[32],"We":[33,75],"consider":[34],"optimized":[35],"(OLT)":[38],"policies,":[39],"a":[40],"recently":[41],"introduced":[42],"family":[43],"hybrid":[45],"techniques,":[46],"which":[47,67],"combine":[48],"advantages":[50,58],"trees":[53],"(high":[54],"precision)":[55],"direct":[60],"policy":[61],"search":[62],"(low":[63],"cost)":[65],"and":[66,97,101],"are":[68],"specifically":[69],"designed":[70],"for":[71],"limited":[72],"budgets.":[74],"present":[76],"two":[77],"extensions":[78],"basic":[81],"OLT":[82],"algorithm":[83],"that":[84,102],"one":[87],"side":[88,106],"allow":[89],"tackling":[90],"deterministic":[91],"optimal":[92],"problems":[94],"large":[96],"continuous":[98],"action":[99],"spaces":[100],"other":[105],"can":[107],"also":[108],"help":[109],"further":[111],"reduce":[112],"complexity.":[115]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}