{"id":"https://openalex.org/W2096338357","doi":"https://doi.org/10.1109/allerton.2010.5707075","title":"Tutor learning using linear constraints in approximate dynamic programming","display_name":"Tutor learning using linear constraints in approximate dynamic programming","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2096338357","doi":"https://doi.org/10.1109/allerton.2010.5707075","mag":"2096338357"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2010.5707075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2010.5707075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","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/A5032709945","display_name":"Dotan Di Castro","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Dotan Di Castro","raw_affiliation_strings":["Faculty of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel","Faculty of Electrical Engineering, Technion\u2014Israel Institute of Technology, 32000 Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Faculty of Electrical Engineering, Technion\u2014Israel Institute of Technology, 32000 Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036260775","display_name":"Shie Mannor","orcid":"https://orcid.org/0000-0003-4439-7647"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shie Mannor","raw_affiliation_strings":["Faculty of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel","Faculty of Electrical Engineering, Technion\u2014Israel Institute of Technology, 32000 Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Faculty of Electrical Engineering, Technion\u2014Israel Institute of Technology, 32000 Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032709945"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15754432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1384","last_page":"1390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9993000030517578,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9883000254631042,"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/computer-science","display_name":"Computer science","score":0.7459796071052551},{"id":"https://openalex.org/keywords/tutor","display_name":"TUTOR","score":0.6279875040054321},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.5844578742980957},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5308787822723389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3966609835624695},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36894533038139343},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3505572974681854},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32537591457366943},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3077681064605713},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14503610134124756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459796071052551},{"id":"https://openalex.org/C2778371403","wikidata":"https://www.wikidata.org/wiki/Q7672049","display_name":"TUTOR","level":2,"score":0.6279875040054321},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.5844578742980957},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5308787822723389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3966609835624695},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36894533038139343},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3505572974681854},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32537591457366943},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3077681064605713},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14503610134124756}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/allerton.2010.5707075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2010.5707075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1576452626","https://openalex.org/W1745373831","https://openalex.org/W1762430620","https://openalex.org/W1964535365","https://openalex.org/W1994123361","https://openalex.org/W1998172110","https://openalex.org/W2040766536","https://openalex.org/W2094364653","https://openalex.org/W2098432798","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2134293360","https://openalex.org/W2153267861","https://openalex.org/W2158479468","https://openalex.org/W2305373430","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W3015571647","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4236078638","https://openalex.org/W4237171445"],"related_works":["https://openalex.org/W2478195092","https://openalex.org/W4312351362","https://openalex.org/W2362145073","https://openalex.org/W2358338760","https://openalex.org/W183073912","https://openalex.org/W2119729863","https://openalex.org/W2887971028","https://openalex.org/W2501172308","https://openalex.org/W2365642790","https://openalex.org/W146785226"],"abstract_inverted_index":{"In":[0,15,37,52,105],"adaptive":[1],"control,":[2],"agents":[3],"interacting":[4],"with":[5],"Markov":[6],"Decision":[7],"Processes":[8],"typically":[9],"face":[10],"two":[11,66],"types":[12],"of":[13,64,71,102],"setups.":[14],"the":[16,19,34,38,41,65,72,81,100,108,117,129],"first":[17],"setup,":[18,40],"environment's":[20,42,73],"model":[21,43,74],"is":[22,44,61,75,83],"known":[23,76],"and":[24,27,46,77],"dynamic":[25],"programming":[26],"related":[28],"methods":[29,49,131],"are":[30,50,132],"used":[31],"to":[32,98,122],"obtain":[33],"optimal":[35,126],"control.":[36],"second":[39],"unknown":[45],"reinforcement":[47],"learning":[48],"used.":[51],"this":[53,90],"work":[54],"we":[55,111],"investigate":[56],"a":[57,62,86,124],"new":[58],"setup":[59],"that":[60],"mix":[63],"mentioned":[67],"setups:":[68],"only":[69],"part":[70],"additional":[78],"information":[79],"regarding":[80],"environment":[82],"provided":[84],"by":[85],"tutor.":[87],"We":[88],"formalize":[89],"problem":[91],"using":[92,107],"linear":[93],"function":[94],"approximation":[95,118],"in":[96,120,134],"order":[97,121],"overcome":[99],"\u201ccurse":[101],"dimensionality\u201d":[103],"phenomenon.":[104],"addition,":[106],"Envelope":[109],"Theorem,":[110],"show":[112],"how":[113],"one":[114],"can":[115],"tune":[116],"basis":[119],"get":[123],"locally":[125],"results.":[127],"Finally,":[128],"suggested":[130],"demonstrated":[133],"simulations.":[135]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}