{"id":"https://openalex.org/W2531640463","doi":null,"title":"PLANS AS A MEANS FOR GUIDING A REINFORCEMENT LEARNER","display_name":"PLANS AS A MEANS FOR GUIDING A REINFORCEMENT LEARNER","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2531640463","mag":"2531640463"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.161.6377","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.6377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ke.informatik.tu-darmstadt.de/lehre/arbeiten/master/2008/Pfau_Jens.pdf","raw_type":"text"},"volume":null,"type":"article","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/A5035510931","display_name":"Jens Pfau","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jens Pfau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5035510931"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"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":0.9345999956130981,"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":0.9345999956130981,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.06480000168085098,"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/T11574","display_name":"Artificial Intelligence in Games","score":9.999999747378752e-05,"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":0.734000027179718},{"id":"https://openalex.org/keywords/plan-reuse","display_name":"plan reuse","score":0.5019999742507935},{"id":"https://openalex.org/keywords/hybrid-agent-architecture","display_name":"hybrid agent architecture","score":0.8029999732971191},{"id":"https://openalex.org/keywords/temporal-knowledge","display_name":"temporal knowledge","score":0.5740000009536743},{"id":"https://openalex.org/keywords/state-abstraction","display_name":"state abstraction","score":0.871999979019165},{"id":"https://openalex.org/keywords/temporal-abstraction","display_name":"temporal abstraction","score":0.9049999713897705},{"id":"https://openalex.org/keywords/learning-time-reduction","display_name":"learning time reduction","score":0.7160000205039978},{"id":"https://openalex.org/keywords/prior-knowledge-integration","display_name":"prior knowledge incorporation","score":0.734000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4522247910499573},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42789697647094727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3318871557712555},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25442811846733093},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1705685555934906}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.161.6377","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.6377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ke.informatik.tu-darmstadt.de/lehre/arbeiten/master/2008/Pfau_Jens.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W5732143","https://openalex.org/W71768770","https://openalex.org/W125541279","https://openalex.org/W134715909","https://openalex.org/W145683767","https://openalex.org/W146200057","https://openalex.org/W163890133","https://openalex.org/W176675522","https://openalex.org/W1258105458","https://openalex.org/W1483184988","https://openalex.org/W1484780672","https://openalex.org/W1488730473","https://openalex.org/W1501936029","https://openalex.org/W1504264720","https://openalex.org/W1527286307","https://openalex.org/W1536990779","https://openalex.org/W1539016358","https://openalex.org/W1556824961","https://openalex.org/W1564534945","https://openalex.org/W1586944634","https://openalex.org/W1594216983","https://openalex.org/W1594602740","https://openalex.org/W1600813180","https://openalex.org/W1607242384","https://openalex.org/W1777239053","https://openalex.org/W1834252692","https://openalex.org/W1968079292","https://openalex.org/W1968768508","https://openalex.org/W1970906492","https://openalex.org/W1982948368","https://openalex.org/W1992535956","https://openalex.org/W1997798784","https://openalex.org/W2004550196","https://openalex.org/W2019501128","https://openalex.org/W2036190613","https://openalex.org/W2040784953","https://openalex.org/W2057113818","https://openalex.org/W2070301851","https://openalex.org/W2085575316","https://openalex.org/W2092919341","https://openalex.org/W2095995891","https://openalex.org/W2097856935","https://openalex.org/W2106086642","https://openalex.org/W2109910161","https://openalex.org/W2114451917","https://openalex.org/W2118710432","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2123354780","https://openalex.org/W2124344619","https://openalex.org/W2135774416","https://openalex.org/W2140256637","https://openalex.org/W2141559645","https://openalex.org/W2143435603","https://openalex.org/W2147492008","https://openalex.org/W2158548602","https://openalex.org/W2159400949","https://openalex.org/W2160395727","https://openalex.org/W2164419340","https://openalex.org/W2165131254","https://openalex.org/W2168691483","https://openalex.org/W2171277043","https://openalex.org/W2171798962","https://openalex.org/W2337392266","https://openalex.org/W2343637401","https://openalex.org/W3011120880"],"related_works":["https://openalex.org/W4312131294","https://openalex.org/W7098175479","https://openalex.org/W2185220979","https://openalex.org/W50377150","https://openalex.org/W7096266329","https://openalex.org/W7119280577","https://openalex.org/W7100008602","https://openalex.org/W2811111819","https://openalex.org/W2057113818","https://openalex.org/W3175128928"],"abstract_inverted_index":{"The":[0,56,84],"complexity":[1],"of":[2,11,44,59,65,71,91,101,110,116,129,137,157,175],"reinforcement":[3,54,131],"learning":[4,127,132],"problems":[5],"grows":[6],"exponentially":[7],"with":[8],"the":[9,12,22,35,42,66,72,92,102,108,114,135,143,170,173],"size":[10],"state":[13,111],"space,":[14],"which":[15,34],"renders":[16],"realistic":[17],"cases":[18],"unsolvable":[19],"and":[20,69,82,113,183,188],"underlines":[21],"need":[23],"for":[24],"guidance.":[25],"This":[26],"thesis":[27],"studies":[28],"a":[29,50,77,124,130,148,151,155,181],"hybrid":[30],"agent":[31,73,144],"architecture,":[32,74],"in":[33,41,76],"toplevel":[36],"module":[37],"reuses":[38],"temporal":[39,119],"knowledge":[40,80,179],"form":[43],"plans":[45,117,176],"that":[46,95,107,159,169],"it":[47],"extracts":[48],"from":[49],"concurrently":[51],"executing":[52],"low-level":[53],"learner.":[55],"first":[57],"contribution":[58,86],"this":[60],"work":[61],"are":[62],"significant":[63],"improvements":[64],"original":[67],"model":[68],"implementation":[70],"resulting":[75],"more":[78],"effective":[79],"extraction":[81],"reuse.":[83],"second":[85],"is":[87,105,145,150],"an":[88],"extensive":[89],"exploration":[90],"synergy":[93],"effects":[94],"take":[96],"place":[97],"between":[98],"both":[99],"layers":[100],"architecture.":[103],"It":[104],"shown":[106],"combination":[109],"abstraction":[112,120],"reuse":[115],"as":[118,177],"can":[121],"lead":[122],"to":[123,139,154,191],"significantly":[125],"shorter":[126],"time":[128],"agent.":[133],"Likewise,":[134],"number":[136],"decisions":[138],"be":[140],"made":[141],"by":[142],"reduced":[146],"because":[147],"plan":[149],"definite":[152],"commitment":[153],"course":[156],"actions":[158],"does":[160],"not":[161],"require":[162],"intermediary":[163],"reasoning.":[164],"In":[165],"addition,":[166],"we":[167],"demonstrate":[168],"architecture":[171],"enables":[172],"integration":[174],"prior":[178],"through":[180],"clear":[182],"convenient":[184],"interface.":[185],"Thus,":[186],"partial":[187],"approximate":[189],"solutions":[190]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-27T00:00:00"}