{"id":"https://openalex.org/W2097451572","doi":"https://doi.org/10.1145/1553374.1553476","title":"Binary action search for learning continuous-action control policies","display_name":"Binary action search for learning continuous-action control policies","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W2097451572","doi":"https://doi.org/10.1145/1553374.1553476","mag":"2097451572"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},"type":"article","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/A5031267271","display_name":"Jason Pazis","orcid":null},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Jason Pazis","raw_affiliation_strings":["Technical University of Crete, Chania, Crete, Greece","Technical University of Crete, Chania - Crete, Greece"],"affiliations":[{"raw_affiliation_string":"Technical University of Crete, Chania, Crete, Greece","institution_ids":["https://openalex.org/I55741626"]},{"raw_affiliation_string":"Technical University of Crete, Chania - Crete, Greece","institution_ids":["https://openalex.org/I55741626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084693234","display_name":"Michail G. Lagoudakis","orcid":"https://orcid.org/0000-0003-2803-3755"},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Michail G. Lagoudakis","raw_affiliation_strings":["Technical University of Crete, Chania, Crete, Greece","Technical University of Crete, Chania - Crete, Greece"],"affiliations":[{"raw_affiliation_string":"Technical University of Crete, Chania, Crete, Greece","institution_ids":["https://openalex.org/I55741626"]},{"raw_affiliation_string":"Technical University of Crete, Chania - Crete, Greece","institution_ids":["https://openalex.org/I55741626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031267271"],"corresponding_institution_ids":["https://openalex.org/I55741626"],"apc_list":null,"apc_paid":null,"fwci":4.5163,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94623299,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"793","last_page":"800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T10142","display_name":"Formal Methods in Verification","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9476000070571899,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7930964231491089},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6390445232391357},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.6370435953140259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5069101452827454},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.43829256296157837},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.43367108702659607},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4044911563396454},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36820468306541443},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36465561389923096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3521808981895447},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07109767198562622}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7930964231491089},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6390445232391357},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.6370435953140259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5069101452827454},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.43829256296157837},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.43367108702659607},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4044911563396454},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36820468306541443},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36465561389923096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3521808981895447},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07109767198562622},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1553374.1553476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.4405","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.4405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.mcgill.ca/~icml2009/papers/532.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.75,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2397817267","display_name":null,"funder_award_id":"MCIRG-CT-2006-044980","funder_id":"https://openalex.org/F4320334962","funder_display_name":"Sixth Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334962","display_name":"Sixth Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1508482627","https://openalex.org/W1515851193","https://openalex.org/W1531900088","https://openalex.org/W1543217731","https://openalex.org/W2035808435","https://openalex.org/W2068052921","https://openalex.org/W2109102709","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2127107099","https://openalex.org/W2127251115","https://openalex.org/W2135396350","https://openalex.org/W2136064843","https://openalex.org/W2145805610","https://openalex.org/W2154549708","https://openalex.org/W2160279936","https://openalex.org/W2569741183","https://openalex.org/W2990138404","https://openalex.org/W3006656721","https://openalex.org/W4214717370","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2006251942","https://openalex.org/W2364741597","https://openalex.org/W1492103595","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W2388509240"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"methods":[2],"for":[3,50,107],"controlling":[4],"stochastic":[5],"processes":[6],"typically":[7],"assume":[8],"a":[9,43],"small":[10],"and":[11,63,97,123,145,148,151,156,166],"discrete":[12],"action":[13,17,38,59,71,92,127],"space.":[14,39,84],"While":[15],"continuous":[16,91,160],"spaces":[18],"are":[19,153],"quite":[20],"common":[21,27],"in":[22,31,129],"real-world":[23],"problems,":[24],"the":[25,37,57,67,70,115,130,159,169],"most":[26],"approach":[28,87,133],"still":[29],"employed":[30],"practice":[32],"is":[33,134],"coarse":[34],"discretization":[35],"of":[36,69,119],"This":[40],"paper":[41],"presents":[42],"novel":[44],"method,":[45],"called":[46],"Binary":[47,111],"Action":[48,112,121],"Search,":[49],"realizing":[51],"continuousaction":[52],"policies":[53],"by":[54],"searching":[55],"efficiently":[56],"entire":[58],"range":[60],"through":[61],"increment":[62],"decrement":[64],"modifications":[65],"to":[66,74,94],"values":[68],"variables":[72],"according":[73],"an":[75,81],"internal":[76],"binary":[77],"policy":[78],"defined":[79],"over":[80],"augmented":[82],"state":[83],"The":[85],"proposed":[86],"essentially":[88],"approximates":[89],"any":[90,102],"space":[93],"arbitrary":[95],"resolution":[96],"can":[98],"be":[99],"combined":[100],"with":[101,136],"discrete-action":[103],"reinforcement":[104,139],"learning":[105,108,140],"algorithm":[106],"continuous-action":[109],"policies.":[110],"Search":[113],"eliminates":[114],"restrictive":[116],"modification":[117],"steps":[118],"Adaptive":[120],"Modification":[122],"requires":[124],"no":[125],"temporal":[126],"locality":[128],"domain.":[131],"Our":[132],"coupled":[135],"two":[137],"well-known":[138],"algorithms":[141],"(Least-Squares":[142],"Policy":[143],"Iteration":[144],"Fitted":[146],"Q-Iteration)":[147],"its":[149],"use":[150],"properties":[152],"thoroughly":[154],"investigated":[155],"demonstrated":[157],"on":[158,168],"state-action":[161],"Inverted":[162],"Pendulum,":[163],"Double":[164],"Integrator,":[165],"Car":[167],"Hill":[170],"domains.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}