{"id":"https://openalex.org/W2144992871","doi":"https://doi.org/10.1109/icsmc.2008.4811303","title":"Learning task decomposition and exploration shaping for reinforcement learning agents","display_name":"Learning task decomposition and exploration shaping for reinforcement learning agents","publication_year":2008,"publication_date":"2008-10-01","ids":{"openalex":"https://openalex.org/W2144992871","doi":"https://doi.org/10.1109/icsmc.2008.4811303","mag":"2144992871"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2008.4811303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2008.4811303","pdf_url":null,"source":{"id":"https://openalex.org/S4210195764","display_name":"Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics","issn_l":"1062-922X","issn":["1062-922X","2577-1655"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"},"type":"conference-paper","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/A5069474617","display_name":"Predrag Djurdjevic","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Predrag Djurdjevic","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","Dept. of Comput. Sci. & Eng., Univ. of Texas at Arlington, Arlington, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Univ. of Texas at Arlington, Arlington, TX","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073400879","display_name":"Manfred Huber","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manfred Huber","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","Dept. of Comput. Sci. & Eng., Univ. of Texas at Arlington, Arlington, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Univ. of Texas at Arlington, Arlington, TX","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189196454"],"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":"4","issue":null,"first_page":"365","last_page":"372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9872000217437744,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8303406238555908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7928227186203003},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6187500357627869},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5989546775817871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5537461638450623},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5383153557777405},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5104974508285522},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4635078012943268},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.45096758008003235},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4410637617111206},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43604573607444763},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4209975302219391},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.41211235523223877},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39161086082458496},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10982075333595276}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8303406238555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928227186203003},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6187500357627869},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5989546775817871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5537461638450623},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5383153557777405},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5104974508285522},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4635078012943268},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.45096758008003235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4410637617111206},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43604573607444763},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4209975302219391},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.41211235523223877},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39161086082458496},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10982075333595276},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2008.4811303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2008.4811303","pdf_url":null,"source":{"id":"https://openalex.org/S4210195764","display_name":"Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics","issn_l":"1062-922X","issn":["1062-922X","2577-1655"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1666476","https://openalex.org/W1492014007","https://openalex.org/W1514587017","https://openalex.org/W1534331386","https://openalex.org/W1553182805","https://openalex.org/W1564190832","https://openalex.org/W1578521162","https://openalex.org/W1592847719","https://openalex.org/W1748123235","https://openalex.org/W1822705290","https://openalex.org/W1880549478","https://openalex.org/W2089561656","https://openalex.org/W2111625828","https://openalex.org/W2112874374","https://openalex.org/W2114451917","https://openalex.org/W2118022839","https://openalex.org/W2126565096","https://openalex.org/W2132284131","https://openalex.org/W2138463816","https://openalex.org/W2143435603","https://openalex.org/W2165792602","https://openalex.org/W6629461247","https://openalex.org/W6633100451","https://openalex.org/W6639342821","https://openalex.org/W6676750447","https://openalex.org/W6676772908","https://openalex.org/W6679661109","https://openalex.org/W6680591503"],"related_works":["https://openalex.org/W2821676139","https://openalex.org/W3043695725","https://openalex.org/W4382138864","https://openalex.org/W4387770285","https://openalex.org/W3022215768","https://openalex.org/W3135975972","https://openalex.org/W3016888008","https://openalex.org/W4385864216","https://openalex.org/W4387183713","https://openalex.org/W2165698076"],"abstract_inverted_index":{"For":[0],"situated":[1],"reinforcement":[2],"learning":[3,35,41,62,102,144,148,204],"agents":[4],"to":[5,14,17,26,32,50,59,83,96,110,125,131,149,199,209,219,233],"succeed":[6],"in":[7,24,120,129,158,182,213,243,251],"complex":[8],"real":[9],"world":[10,256],"environments":[11],"they":[12,64],"have":[13,56,107],"be":[15],"able":[16],"efficiently":[18],"acquire":[19],"and":[20,31,48,52,95,124,155,203,228,248],"reuse":[21],"control":[22,53],"knowledge":[23,99],"order":[25,130],"accomplish":[27],"new":[28,37,54,89,122,127,163,222],"tasks":[29,55,128,250],"faster":[30],"accelerate":[33],"the":[34,57,67,73,101,108,112,151,159,173,183,201,207,216,221,225,230,244],"of":[36,69,76,114,153,161,193,206,215,229,246],"policies.":[38],"While":[39],"hierarchical":[40],"approaches":[42],"which":[43,176],"transfer":[44],"previously":[45],"acquired":[46],"skills":[47],"representations":[49],"model":[51],"potential":[58],"significantly":[60],"improve":[61,98],"times,":[63],"also":[65,106],"pose":[66],"risk":[68],"ldquobehavior":[70],"proliferationrdquo":[71],"where":[72],"growing":[74],"set":[75,192],"available":[77,178],"actions":[78],"makes":[79],"it":[80],"increasingly":[81],"difficult":[82],"determine":[84],"a":[85,88,121,140,162,191,252],"strategy":[86],"for":[87,143,168],"task.":[90],"To":[91],"overcome":[92],"this":[93],"problem":[94],"further":[97],"reuse,":[100],"agent":[103,208],"should":[104],"thus":[105],"ability":[109,239],"predict":[111,150],"utility":[113,152,194],"an":[115,235],"action":[116,179],"or":[117],"reusable":[118],"skill":[119],"context":[123,160,245],"analyze":[126],"decompose":[132],"them":[133],"into":[134],"known":[135],"subtasks.":[136],"This":[137,187,238],"paper":[138],"presents":[139],"novel":[141],"approach":[142],"task":[145,185],"decomposition":[146],"by":[147,171],"subgoals":[154],"subgoal":[156],"types":[157],"task,":[164],"as":[165,167,190],"well":[166],"exploration":[169,202],"shaping":[170],"predicting":[172],"likelihood":[174],"with":[175],"each":[177],"is":[180,196,240],"useful":[181],"given":[184],"context.":[186],"information,":[188],"encoded":[189],"functions,":[195],"then":[197],"used":[198],"focus":[200],"process":[205],"increase":[210],"performance":[211],"both":[212],"terms":[214],"time":[217,227,231],"spent":[218],"reach":[220],"task's":[223],"goal":[224],"first":[226],"required":[232],"learn":[234],"optimal":[236],"policy.":[237],"demonstrated":[241],"here":[242],"navigation":[247],"manipulation":[249],"feature":[253],"enhanced":[254],"grid":[255],"domain.":[257]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}