{"id":"https://openalex.org/W144463461","doi":null,"title":"Planning with Neural Networks and Reinforcement Learning","display_name":"Planning with Neural Networks and Reinforcement Learning","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W144463461","mag":"144463461"},"language":"en","primary_location":{"id":"pmh:oai:pumaoai.isti.cnr.it:cnr.istc/cnr.istc/2002-PHD-001","doi":null,"is_oa":true,"landing_page_url":"http://puma.isti.cnr.it/dfdownloadnew.php?ident=cnr.istc/cnr.istc/2002-PHD-001","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Computer Science, University of Essex. Ph.D. Dissertation, 2002.","raw_type":"info:eu-repo/semantics/doctoralThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://puma.isti.cnr.it/dfdownloadnew.php?ident=cnr.istc/cnr.istc/2002-PHD-001","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076711458","display_name":"Gianluca Baldassarre","orcid":"https://orcid.org/0000-0002-1277-4447","observed_orcids":["https://orcid.org/0000-0002-1277-4447"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gianluca Baldassarre","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1277-4447","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5076711458"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"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":0.9916999936103821,"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":0.9916999936103821,"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":0.007799999788403511,"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/actor-critic-reinforcement-learning","display_name":"actor-critic reinforcement learning","score":0.8939999938011169},{"id":"https://openalex.org/keywords/predictive-planning","display_name":"predictive planning","score":0.5789999961853027},{"id":"https://openalex.org/keywords/landmark-navigation","display_name":"landmark navigation","score":0.6460000276565552},{"id":"https://openalex.org/keywords/mixture-of-experts","display_name":"mixture of experts","score":0.722000002861023},{"id":"https://openalex.org/keywords/abstract-planning","display_name":"abstract planning","score":0.7200000286102295},{"id":"https://openalex.org/keywords/modular-neural-architecture","display_name":"modular neural architecture","score":0.7289999723434448},{"id":"https://openalex.org/keywords/robot-controller","display_name":"robot controller","score":0.4230000078678131}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8441689014434814},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6194204688072205},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5695611238479614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5592108368873596},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.4456920921802521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.422829270362854},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23671433329582214},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.07722851634025574}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:pumaoai.isti.cnr.it:cnr.istc/cnr.istc/2002-PHD-001","doi":null,"is_oa":true,"landing_page_url":"http://puma.isti.cnr.it/dfdownloadnew.php?ident=cnr.istc/cnr.istc/2002-PHD-001","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Computer Science, University of Essex. Ph.D. Dissertation, 2002.","raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"mag:144463461","doi":null,"is_oa":false,"landing_page_url":"https://www.researchgate.net/profile/Gianluca_Baldassarre/publication/34267612_Planning_with_neural_networks_and_reinforcement_learning_/links/0046351f0c0d7b63a3000000.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":{"id":"pmh:oai:pumaoai.isti.cnr.it:cnr.istc/cnr.istc/2002-PHD-001","doi":null,"is_oa":true,"landing_page_url":"http://puma.isti.cnr.it/dfdownloadnew.php?ident=cnr.istc/cnr.istc/2002-PHD-001","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Computer Science, University of Essex. Ph.D. Dissertation, 2002.","raw_type":"info:eu-repo/semantics/doctoralThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":123,"referenced_works":["https://openalex.org/W3942861","https://openalex.org/W10620669","https://openalex.org/W38453897","https://openalex.org/W51389567","https://openalex.org/W65738273","https://openalex.org/W77412865","https://openalex.org/W79676656","https://openalex.org/W91815983","https://openalex.org/W125252782","https://openalex.org/W133237934","https://openalex.org/W133833791","https://openalex.org/W142048064","https://openalex.org/W156063826","https://openalex.org/W157797980","https://openalex.org/W184814775","https://openalex.org/W207822505","https://openalex.org/W592196538","https://openalex.org/W1480676279","https://openalex.org/W1480895035","https://openalex.org/W1481659984","https://openalex.org/W1488771041","https://openalex.org/W1491843047","https://openalex.org/W1493733731","https://openalex.org/W1494474274","https://openalex.org/W1498436455","https://openalex.org/W1499371387","https://openalex.org/W1504212531","https://openalex.org/W1514205146","https://openalex.org/W1535810436","https://openalex.org/W1541084404","https://openalex.org/W1545984840","https://openalex.org/W1546197084","https://openalex.org/W1549249986","https://openalex.org/W1555519929","https://openalex.org/W1555801537","https://openalex.org/W1567249951","https://openalex.org/W1567512734","https://openalex.org/W1573706465","https://openalex.org/W1579756385","https://openalex.org/W1583833196","https://openalex.org/W1583882820","https://openalex.org/W1597939856","https://openalex.org/W1607674437","https://openalex.org/W1610678877","https://openalex.org/W1612069379","https://openalex.org/W1613651675","https://openalex.org/W1640358294","https://openalex.org/W1754468829","https://openalex.org/W1819200667","https://openalex.org/W1823011326","https://openalex.org/W1864838508","https://openalex.org/W1886499571","https://openalex.org/W1916146537","https://openalex.org/W1969483458","https://openalex.org/W1979356863","https://openalex.org/W1980960668","https://openalex.org/W1981627423","https://openalex.org/W1981799875","https://openalex.org/W1994030467","https://openalex.org/W1998890282","https://openalex.org/W2009533501","https://openalex.org/W2017338426","https://openalex.org/W2021061679","https://openalex.org/W2035446426","https://openalex.org/W2038727204","https://openalex.org/W2041314294","https://openalex.org/W2042043681","https://openalex.org/W2047057213","https://openalex.org/W2052117683","https://openalex.org/W2070619758","https://openalex.org/W2090138478","https://openalex.org/W2097571405","https://openalex.org/W2097856935","https://openalex.org/W2098432798","https://openalex.org/W2102000945","https://openalex.org/W2107019937","https://openalex.org/W2107726111","https://openalex.org/W2110485445","https://openalex.org/W2111428077","https://openalex.org/W2111438441","https://openalex.org/W2112032710","https://openalex.org/W2118127772","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2123956999","https://openalex.org/W2124175081","https://openalex.org/W2124776405","https://openalex.org/W2126141328","https://openalex.org/W2128084896","https://openalex.org/W2135995262","https://openalex.org/W2140265998","https://openalex.org/W2141559645","https://openalex.org/W2141714215","https://openalex.org/W2142592520","https://openalex.org/W2147677349","https://openalex.org/W2149611281","https://openalex.org/W2150039829","https://openalex.org/W2150470619","https://openalex.org/W2150884987","https://openalex.org/W2151742051","https://openalex.org/W2153562927","https://openalex.org/W2155027007","https://openalex.org/W2155566009","https://openalex.org/W2157445228","https://openalex.org/W2160067530","https://openalex.org/W2160108997","https://openalex.org/W2162164385","https://openalex.org/W2162892219","https://openalex.org/W2162909869","https://openalex.org/W2166614928","https://openalex.org/W2168939893","https://openalex.org/W2170317651","https://openalex.org/W2247226361","https://openalex.org/W2337392266","https://openalex.org/W2341171179","https://openalex.org/W2343637401","https://openalex.org/W2401788879","https://openalex.org/W2568058616","https://openalex.org/W2912185451","https://openalex.org/W2912225506","https://openalex.org/W3011120880","https://openalex.org/W3021909058","https://openalex.org/W3139377883"],"related_works":["https://openalex.org/W7097057618","https://openalex.org/W1530139808","https://openalex.org/W7014324169","https://openalex.org/W2119537428","https://openalex.org/W761371030","https://openalex.org/W3114457554","https://openalex.org/W2134859459","https://openalex.org/W2600009170","https://openalex.org/W7100529021","https://openalex.org/W4387885929"],"abstract_inverted_index":{"This":[0,112,157,197],"thesis":[1],"presents":[2],"the":[3,37,64,76,79,87,103,147,152,155,169,186,191,200,204,223,259,268],"design,":[4],"implementation":[5],"and":[6,15,33,60,72,127,150,188,213,261,284,292,300],"investigation":[7],"of":[8,36,58,78,89,116,130,143,154,218,226,238,255,277,290],"some":[9,163],"predictive-planning":[10],"controllers":[11,40,303],"built":[12],"with":[13,43,242,297,301,313],"neural-networks":[14],"inspired":[16],"by":[17,63,162],"Dyna-PI":[18,22,104],"architectures":[19,23],"(Sutton,":[20],"1990).":[21],"are":[24,41,137],"planning":[25,208,280,299],"systems":[26],"based":[27,91],"on":[28,66,92,122,203],"actor-critic":[29],"reinforcement":[30,70,307],"learning":[31,232,308],"methods":[32],"a":[34,44,49,109,118,215,245,253,262,274],"model":[35,153,158],"environment.":[38,156],"The":[39,81,270],"tested":[42],"simulated":[45],"robot":[46],"that":[47,181,251,305],"solves":[48],"stochastic":[50],"path-finding":[51],"landmark":[52],"navigation":[53],"task.":[54],"A":[55,95,177],"critical":[56],"review":[57,82],"ideas":[59,84],"models":[61],"proposed":[62],"literature":[65],"problem":[67],"solving,":[68],"planning,":[69],"learning,":[71],"neural":[73,93,164,227,247,278],"networks":[74,165,228],"precedes":[75],"presentation":[77],"controllers.":[80],"isolates":[83],"relevant":[85],"to":[86,132,167],"design":[88],"planners":[90],"networks.":[94],"\"neural":[96,178],"forward":[97,189],"planner\"":[98,180],"is":[99,106,114,128,159,175,194,249],"implemented":[100],"that,":[101],"unlike":[102],"architectures,":[105],"taskable":[107],"in":[108,288],"strong":[110],"sense.":[111],"planner":[113,198],"capable":[115,129],"building":[117],"\"partial":[119],"policy\"":[120],"focussed":[121],"around":[123,209],"efficient":[124,210],"start-goal":[125,211],"paths,":[126,212],"deciding":[131],"re-plan":[133],"if":[134],"\"unexpected\"":[135],"states":[136],"encountered.":[138],"Planning":[139],"iteratively":[140],"generates":[141,182],"\"chains":[142],"predictions\"":[144],"starting":[145],"from":[146,185,190],"current":[148,192],"state":[149,193],"using":[151],"made":[160],"up":[161],"trained":[166],"predict":[168],"next":[170],"input":[171],"when":[172],"an":[173],"action":[174],"executed.":[176],"bidirectional":[179],"trajectories":[183],"backward":[184],"goal":[187],"also":[195,235,272],"implemented.":[196],"exploits":[199],"knowledge":[201],"(image)":[202],"goal,":[205],"further":[206],"focuses":[207],"produces":[214],"quicker":[216],"updating":[217],"evaluations.":[219],"In":[220],"several":[221],"experiments":[222,296],"generalisation":[224],"capacity":[225],"proves":[229],"important":[230],"for":[231,258,267],"but":[233],"it":[234],"causes":[236],"problems":[237,244,311],"interference.":[239],"To":[240],"deal":[241],"these":[243],"modular":[246,265],"architecture":[248],"implemented,":[250],"uses":[252],"mixture":[254],"experts":[256],"network":[257,266],"critic,":[260],"simple":[263,275],"hierarchical":[264],"actor.":[269],"research":[271],"implements":[273],"form":[276],"abstract":[279],"named":[281],"\"coarse":[282],"planning\",":[283],"investigates":[285],"its":[286],"strengths":[287],"terms":[289],"exploration":[291],"evaluations'":[293],"updating.":[294],"Some":[295],"coarse":[298],"other":[302],"suggest":[304],"discounted":[306],"may":[309],"have":[310],"dealing":[312],"long-lasting":[314],"tasks.":[315]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2016-06-24T00:00:00"}