{"id":"https://openalex.org/W6964962354","doi":"https://doi.org/10.26190/unsworks/21271","title":"Heterogeneous representations for reinforcement learning control of dynamic systems","display_name":"Heterogeneous representations for reinforcement learning control of dynamic systems","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W6964962354","doi":"https://doi.org/10.26190/unsworks/21271"},"language":"en","primary_location":{"id":"pmh:oai:unsworks.unsw.edu.au:1959.4/19350","is_oa":true,"landing_page_url":"http://handle.unsw.edu.au/1959.4/19350","pdf_url":"http://handle.unsw.edu.au/1959.4/19350","source":{"id":"https://openalex.org/S4377196481","display_name":"UNSWorks (UNSW Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31746571","host_organization_name":"UNSW Sydney","host_organization_lineage":["https://openalex.org/I31746571"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://handle.unsw.edu.au/1959.4/19350","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"McGarity, Michael","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"McGarity, Michael","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12713","display_name":"Forest Ecology and Biodiversity Studies","score":0.16830000281333923,"subfield":{"id":"https://openalex.org/subfields/1109","display_name":"Insect Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12713","display_name":"Forest Ecology and Biodiversity Studies","score":0.16830000281333923,"subfield":{"id":"https://openalex.org/subfields/1109","display_name":"Insect Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11753","display_name":"Forest Management and Policy","score":0.1517000049352646,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.08129999786615372,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.6875},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5889999866485596},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5674999952316284},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5264999866485596},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5152000188827515},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.48510000109672546},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4708999991416931},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4458000063896179}],"concepts":[{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6003000140190125},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5674999952316284},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5264999866485596},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5152000188827515},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41350001096725464},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.35350000858306885},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31619998812675476},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28139999508857727},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.26660001277923584}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:unsworks.unsw.edu.au:1959.4/19350","is_oa":true,"landing_page_url":"http://handle.unsw.edu.au/1959.4/19350","pdf_url":"http://handle.unsw.edu.au/1959.4/19350","source":{"id":"https://openalex.org/S4377196481","display_name":"UNSWorks (UNSW Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31746571","host_organization_name":"UNSW Sydney","host_organization_lineage":["https://openalex.org/I31746571"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/19350","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.4/19350","pdf_url":null,"source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_db06"},{"id":"doi:10.26190/unsworks/21271","is_oa":true,"landing_page_url":"https://doi.org/10.26190/unsworks/21271","pdf_url":null,"source":{"id":"https://openalex.org/S7407053176","display_name":"University of New South Wales","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"pmh:oai:unsworks.unsw.edu.au:1959.4/19350","is_oa":true,"landing_page_url":"http://handle.unsw.edu.au/1959.4/19350","pdf_url":"http://handle.unsw.edu.au/1959.4/19350","source":{"id":"https://openalex.org/S4377196481","display_name":"UNSWorks (UNSW Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31746571","host_organization_name":"UNSW Sydney","host_organization_lineage":["https://openalex.org/I31746571"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7037427425384521,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W6964962354.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Intelligent":[0],"agents":[1,29],"are":[2,48,285],"designed":[3],"to":[4,33,35,49,66,125,136,158,199,269,316,329,346],"interact":[5],"with,":[6],"and":[7,65,90,92,144,195,204,217,278,302,336],"learn":[8,108],"about,":[9],"their":[10],"environment":[11],"so":[12],"that":[13,82,94,323],"they":[14],"can":[15],"act":[16],"purposefully":[17],"towards":[18],"a":[19,39,51,75,109,126,138,141,145,150,173,215,233,261,270,291,300,318,338,344,347],"goal.":[20],"One":[21],"class":[22,147,292],"of":[23,45,57,77,148,172,192,208,227,244,260,281,290,293,311,340],"problems":[24],"encountered":[25],"in":[26,102,178,264,307,333],"building":[27],"such":[28,81,93],"is":[30,86,156,185,235,327],"learning":[31,272,314],"how":[32],"respond":[34],"dynamic":[36,59,161],"systems":[37,60,117,162],"with":[38,61,163,309],"continuous":[40,62,79,114],"state":[41,64,115,175],"space.":[42],"The":[43,153,170,206,225],"goals":[44],"this":[46,68,254,305],"dissertation":[47],"develop":[50],"framework":[52,69],"for":[53,112,132,240],"understanding":[54],"the":[55,78,83,95,119,133,179,182,190,211,222,229,238,245,258,275,279,288],"behaviour":[56,171,259],"partitioned":[58,84,113,120,134,160,174],"underlying":[63],"translate":[67],"into":[70],"algorithms":[71,106,297,315],"which":[72,107,256],"adaptively":[73,298],"form":[74],"partition":[76,306],"space":[80,116,176],"system":[85,121,135,177],"more":[87],"easily":[88,100],"learned":[89],"controlled,":[91],"control":[96,110,223,319],"law":[97],"may":[98],"be":[99,137],"explained":[101],"intuitive":[103,242],"ways.":[104],"Currently,":[105],"policy":[111,320],"treat":[118],"as":[122,232,237,287],"an":[123,241,250],"approximation":[124],"Markov":[127,139,276],"chain.":[128],"I":[129,188,248],"give":[130],"conditions":[131],"chain,":[140],"semi-Markov":[142],"process":[143],"new":[146],"system,":[149],"weak-semi-Markov":[151,154],"process.":[152],"model":[155,159],"shown":[157,328],"greater":[164],"economy":[165],"than":[166],"other":[167],"surveyed":[168],"models.":[169],"area":[180],"around":[181],"region":[183,201],"boundaries":[184],"also":[186],"considered.":[187],"use":[189,304],"theory":[191,280],"sliding":[193,230],"surfaces,":[194],"some":[196],"heuristic":[197],"arguments":[198],"recommend":[200],"boundary":[202],"shape":[203],"position.":[205],"concept":[207,226,255],"'staying":[209],"on":[210,253,322],"boundary'":[212],"then":[213],"becomes":[214],"robust":[216],"relatively":[218],"easy":[219],"subgoal":[220,234],"within":[221],"algorithm.":[224],"'reaching":[228],"surface'":[231],"used":[236,286],"basis":[239,289],"explanation":[243],"learnt":[246,262],"controller.":[247],"present":[249],"algorithm":[251],"based":[252,321],"explains":[257],"controller":[263],"ways":[265],"not":[266],"previously":[267],"available":[268],"machine":[271],"algorithms.":[273,295],"Finally,":[274],"Property":[277],"Sliding":[282],"Mode":[283],"Control":[284],"recursive":[294],"These":[296],"find":[299,317],"partition,":[301],"simultaneously":[303],"conjunction":[308],"one":[310],"five":[312],"reinforcement":[313],"partition.":[324],"This":[325],"technique":[326],"work":[330],"very":[331],"well":[332],"learning,":[334],"controlling":[335],"explaining":[337],"variety":[339],"physical":[341],"systems,":[342],"from":[343],"monorail":[345],"container":[348],"crane.":[349]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}