{"id":"https://openalex.org/W2605153772","doi":null,"title":"Leveraging attention focus for effective reinforcement learning in complex domains","display_name":"Leveraging attention focus for effective reinforcement learning in complex domains","publication_year":2013,"publication_date":"2013-03-29","ids":{"openalex":"https://openalex.org/W2605153772","mag":"2605153772"},"language":"en","primary_location":{"id":"pmh:oai:smartech.gatech.edu:1853/47618","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/1853/47618","pdf_url":null,"source":{"id":"https://openalex.org/S4377196313","display_name":"SMARTech Repository (Georgia Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I130701444","host_organization_name":"Georgia Institute of Technology","host_organization_lineage":["https://openalex.org/I130701444"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5078739429","display_name":"Cobo Rus","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cobo Rus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018974904","display_name":"Lu\u00eds Carlos","orcid":"https://orcid.org/0000-0001-8005-9886","observed_orcids":["https://orcid.org/0000-0001-8005-9886"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu\u00eds Carlos","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8005-9886","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/attentional-focus","display_name":"attentional focus","score":0.9810000061988831},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8650000095367432},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.8899999856948853},{"id":"https://openalex.org/keywords/state-abstraction","display_name":"state abstraction","score":0.7059999704360962},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.6600000262260437},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.7559999823570251},{"id":"https://openalex.org/keywords/subtask-decomposition","display_name":"subtask decomposition","score":0.7239999771118164},{"id":"https://openalex.org/keywords/high-dimensional-state-spaces","display_name":"high-dimensional state spaces","score":0.6539999842643738},{"id":"https://openalex.org/keywords/autonomous-agents","display_name":"autonomous agents","score":0.4359999895095825},{"id":"https://openalex.org/keywords/robotic-assistants","display_name":"robotic assistants","score":0.4830000102519989}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7049905061721802},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6047119498252869},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5831048488616943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4064781665802002},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.36830341815948486},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3632439970970154},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.36277496814727783},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32907140254974365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31857210397720337},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12411481142044067},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:smartech.gatech.edu:1853/47618","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/1853/47618","pdf_url":null,"source":{"id":"https://openalex.org/S4377196313","display_name":"SMARTech Repository (Georgia Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I130701444","host_organization_name":"Georgia Institute of Technology","host_organization_lineage":["https://openalex.org/I130701444"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},{"id":"mag:2605153772","doi":null,"is_oa":false,"landing_page_url":"https://smartech.gatech.edu/bitstream/1853/47618/1/cobo-rus_luis-carlos_201305_phd.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W72400652","https://openalex.org/W171213352","https://openalex.org/W1488730473","https://openalex.org/W1495061682","https://openalex.org/W1505937442","https://openalex.org/W1532534028","https://openalex.org/W1541084404","https://openalex.org/W1576379491","https://openalex.org/W1582485033","https://openalex.org/W1593369214","https://openalex.org/W1598052524","https://openalex.org/W1601974704","https://openalex.org/W1640646391","https://openalex.org/W1678414046","https://openalex.org/W1726275262","https://openalex.org/W1826106524","https://openalex.org/W1968768508","https://openalex.org/W1971014294","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2011233848","https://openalex.org/W2014932765","https://openalex.org/W2020753891","https://openalex.org/W2024060531","https://openalex.org/W2031355581","https://openalex.org/W2052684427","https://openalex.org/W2069192723","https://openalex.org/W2073384958","https://openalex.org/W2075268401","https://openalex.org/W2106216496","https://openalex.org/W2107628283","https://openalex.org/W2109910161","https://openalex.org/W2111020392","https://openalex.org/W2116157560","https://openalex.org/W2116339921","https://openalex.org/W2118022839","https://openalex.org/W2118556122","https://openalex.org/W2121863487","https://openalex.org/W2122480991","https://openalex.org/W2122701159","https://openalex.org/W2124125910","https://openalex.org/W2125055259","https://openalex.org/W2126410641","https://openalex.org/W2127572219","https://openalex.org/W2128547596","https://openalex.org/W2130005627","https://openalex.org/W2134598164","https://openalex.org/W2136202932","https://openalex.org/W2138326839","https://openalex.org/W2143435603","https://openalex.org/W2155027007","https://openalex.org/W2158738729","https://openalex.org/W2160808139","https://openalex.org/W2161336914","https://openalex.org/W2161485371","https://openalex.org/W3020831056","https://openalex.org/W4321428174","https://openalex.org/W7124149927","https://openalex.org/W7124166422"],"related_works":["https://openalex.org/W3099671379","https://openalex.org/W6940219326","https://openalex.org/W2572935813","https://openalex.org/W2991344719","https://openalex.org/W7095738860","https://openalex.org/W6941197146","https://openalex.org/W7125524962","https://openalex.org/W7098062532","https://openalex.org/W7098719960","https://openalex.org/W7100858647"],"abstract_inverted_index":{"One":[0],"of":[1,8,39,71,80,85,124,142,157,170,177,199,239,259,329,345,360,374,399,421],"the":[2,6,37,81,86,121,125,140,168,178,197,237,240,251,265,267,293,323,366,375,379,384],"hardest":[3],"challenges":[4],"in":[5,19,61,145,232,292,382],"field":[7],"machine":[9],"learning":[10,43,46,135,206],"is":[11,403],"to":[12,34,92,101,106,139,196,253,325,332,406],"build":[13],"agents,":[14],"such":[15,102,219],"as":[16,220],"robotic":[17],"assistants":[18],"homes":[20],"and":[21,45,83,153,208,297,314,331],"hospitals,":[22],"that":[23,29,113,115,163,287,402,418],"can":[24,128,166,185,288,306,424],"autonomously":[25],"learn":[26,93],"new":[27,94],"tasks":[28,95],"they":[30,57,243],"were":[31],"not":[32,98,356],"pre-programmed":[33],"tackle,":[35],"without":[36],"intervention":[38],"an":[40,107,334,371,397],"engineer.":[41],"Reinforcement":[42],"(RL)":[44],"from":[47,247,256,261,282,316,370],"demonstration":[48,283],"(LfD)":[49],"are":[50,58,230],"popular":[51],"approaches":[52],"for":[53,337,427],"task":[54,266],"learning,":[55],"but":[56],"often":[59],"ineffective":[60],"high-dimensional":[62],"domains":[63,408],"unless":[64],"provided":[65],"with":[66,137,181,194,204,213,351,378,396,412],"either":[67],"a":[68,76,155,174,257,299,303,327,352,358],"great":[69],"deal":[70],"problem-specific":[72],"domain":[73,103],"information":[74,104,242,369,423],"or":[75,222],"carefully":[77],"crafted":[78],"representation":[79,176],"state":[82,126,143,179,295],"dynamics":[84],"world.":[87],"Unfortunately,":[88],"autonomous":[89],"agents":[90],"trying":[91],"usually":[96],"do":[97,149],"have":[99],"access":[100],"nor":[105],"appropriate":[108,335],"representation.":[109],"\\n":[110,225,341],"\\nWe":[111],"demonstrate":[112],"algorithms":[114,136,165,207,218,229,274,346],"focus,":[116],"at":[117,394],"each":[118,338,413],"moment,":[119],"on":[120,236,255],"relevant":[122],"features":[123,144,200,252,286],"space":[127,180,296],"achieve":[129],"significant":[130],"speed-ups":[131,193,210],"over":[132],"previous":[133],"reinforcement":[134],"respect":[138,195],"number":[141,198],"complex":[146,171],"domains.":[147],"To":[148],"so,":[150],"we":[151,347,389,416],"introduce":[152,272,390],"evaluate":[154],"family":[156],"attention":[158,227,349,367],"focus":[159,228,241,246,254,350,368,422],"algorithms.":[160],"We":[161,271],"show":[162,417],"these":[164],"reduce":[167],"dimensionality":[169],"domains,":[172],"creating":[173],"compact":[175],"which":[182],"satisficing":[183,304],"policies":[184],"be":[186,289,307,425],"learned":[187,308],"efficiently.":[188,309],"Our":[189],"approach":[190],"obtains":[191],"exponential":[192],"considered":[201],"when":[202,211],"compared":[203,212],"table-based":[205],"polynomial":[209],"state-of-the-art":[214],"function":[215],"approximation":[216],"RL":[217],"LSPI":[221],"fitted":[223],"Q-learning.":[224],"\\nOur":[226],"divided":[231],"two":[233,273],"classes,":[234],"depending":[235],"source":[238],"require.":[244],"Attention":[245],"human":[248,262,361],"demonstrations":[249,260,324],"infers":[250],"set":[258,328,359],"teachers":[263],"performing":[264,383],"agent":[268,380],"must":[269],"learn.":[270],"within":[275],"this":[276,387],"class.":[277],"The":[278,310],"first":[279,395],"one,":[280],"abstraction":[281,301,315,336],"(AfD),":[284],"identifies":[285],"safely":[290],"ignored":[291],"whole":[294],"builds":[298],"state-space":[300],"where":[302,409],"policy":[305],"second,":[311],"automatic":[312],"decomposition":[313],"demonstration,":[317],"goes":[318],"one":[319],"step":[320],"further,":[321],"using":[322],"identify":[326],"subtasks":[330],"find":[333],"subtask":[339],"found.":[340],"\\nThe":[342],"other":[343],"class":[344],"present,":[348],"world":[353,376],"model,":[354],"does":[355],"require":[357],"demonstrations.":[362],"Instead,":[363],"it":[364],"extracts":[365],"object-based":[372],"model":[373],"together":[377],"experience":[381],"task.":[385],"Within":[386],"class,":[388],"object-focused":[391],"Q-learning":[392],"(OF-Q),":[393],"assumption":[398],"object":[400],"independence":[401],"later":[404],"removed":[405],"support":[407],"objects":[410],"interact":[411],"other.":[414],"Finally,":[415],"both":[419],"sources":[420],"combined":[426],"further":[428],"speed-ups.":[429]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2017-04-14T00:00:00"}