{"id":"https://openalex.org/W1961984579","doi":null,"title":"Consolidated Deep Actor Critic Networks","display_name":"Consolidated Deep Actor Critic Networks","publication_year":2015,"publication_date":"2015-09-30","ids":{"openalex":"https://openalex.org/W1961984579","mag":"1961984579"},"language":"en","primary_location":{"id":"pmh:oai:tudelft.nl:uuid:682a56ed-8e21-4b70-af11-0e8e9e298fa2","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:682a56ed-8e21-4b70-af11-0e8e9e298fa2","pdf_url":"http://resolver.tudelft.nl/uuid:682a56ed-8e21-4b70-af11-0e8e9e298fa2","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://resolver.tudelft.nl/uuid:682a56ed-8e21-4b70-af11-0e8e9e298fa2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075035647","display_name":"T.A. Van der Laan","orcid":"https://orcid.org/0009-0008-1911-1567","observed_orcids":["https://orcid.org/0009-0008-1911-1567"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"T.A. Van der Laan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0008-1911-1567","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5075035647"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","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/actor-critic-reinforcement-learning","display_name":"actor-critic reinforcement learning","score":0.7009999752044678},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.7009999752044678},{"id":"https://openalex.org/keywords/continuous-action-control","display_name":"continuous action control","score":0.8069999814033508},{"id":"https://openalex.org/keywords/acrobot","display_name":"Acrobot","score":0.781000018119812},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.5419999957084656}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.753929078578949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6961941719055176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6139074563980103},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5668888688087463},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5619060397148132},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44369176030158997},{"id":"https://openalex.org/C2778091849","wikidata":"https://www.wikidata.org/wiki/Q4959649","display_name":"Breakout","level":2,"score":0.4377542734146118},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4242023229598999},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.417322039604187},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:tudelft.nl:uuid:682a56ed-8e21-4b70-af11-0e8e9e298fa2","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:682a56ed-8e21-4b70-af11-0e8e9e298fa2","pdf_url":"http://resolver.tudelft.nl/uuid:682a56ed-8e21-4b70-af11-0e8e9e298fa2","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},{"id":"mag:1961984579","doi":null,"is_oa":false,"landing_page_url":"http://repository.tudelft.nl/islandora/object/uuid%3A682a56ed-8e21-4b70-af11-0e8e9e298fa2/datastream/OBJ/download","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:tudelft.nl:uuid:682a56ed-8e21-4b70-af11-0e8e9e298fa2","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:682a56ed-8e21-4b70-af11-0e8e9e298fa2","pdf_url":"http://resolver.tudelft.nl/uuid:682a56ed-8e21-4b70-af11-0e8e9e298fa2","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1961984579.pdf","grobid_xml":"https://content.openalex.org/works/W1961984579.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W166862392","https://openalex.org/W613766092","https://openalex.org/W1506832649","https://openalex.org/W1541084404","https://openalex.org/W1547105496","https://openalex.org/W1595483645","https://openalex.org/W1646707810","https://openalex.org/W1665214252","https://openalex.org/W1757796397","https://openalex.org/W1836465849","https://openalex.org/W2028145673","https://openalex.org/W2089434629","https://openalex.org/W2101539915","https://openalex.org/W2107855852","https://openalex.org/W2112796928","https://openalex.org/W2117731089","https://openalex.org/W2120346334","https://openalex.org/W2131600418","https://openalex.org/W2136064843","https://openalex.org/W2145339207","https://openalex.org/W2147786979","https://openalex.org/W2156347136","https://openalex.org/W2158462832","https://openalex.org/W2165150801","https://openalex.org/W2341171179","https://openalex.org/W2575731723","https://openalex.org/W2949117887","https://openalex.org/W2953334758","https://openalex.org/W2964121744","https://openalex.org/W3011120880","https://openalex.org/W3121926921","https://openalex.org/W3176583243"],"related_works":["https://openalex.org/W1433753992","https://openalex.org/W3038733812","https://openalex.org/W3199207920","https://openalex.org/W4395111779","https://openalex.org/W4406657620","https://openalex.org/W4200306064","https://openalex.org/W2769883686","https://openalex.org/W4307314919","https://openalex.org/W2790921766","https://openalex.org/W4409257941"],"abstract_inverted_index":{"The":[0],"works":[1],"[Volodymyr":[2,16],"et":[3,17],"al.":[4,18],"Playing":[5],"atari":[6],"with":[7,37,54,119,152],"deep":[8,22,34,43,116,138,175],"reinforcement":[9,23],"learning.":[10,24,40],"arXiv":[11],"preprint":[12],"arXiv:1312.5602,":[13],"2013.]":[14],"and":[15,70,77,150,164,186,207],"Human-level":[19],"control":[20,93],"through":[21],"Nature,":[25],"518(7540):529\u2013533,":[26],"2015.]":[27],"have":[28,124],"demonstrated":[29],"the":[30,64,82,101,125,144,157,162,184,196],"power":[31],"of":[32,136],"combining":[33],"neural":[35,117],"networks":[36,45,118,141,166,178,188],"Watkins":[38],"Q":[39,44,55],"They":[41],"introduce":[42],"(DQN)":[46],"that":[47,182],"learn":[48,67],"to":[49,59,66,86,92,103,114,127,155,191],"associate":[50],"High":[51],"dimensional":[52],"inputs":[53],"values":[56],"in":[57,198],"order":[58],"produce":[60],"discrete":[61,87],"actions,":[62],"allowing":[63],"system":[65,83,197],"complex":[68,95],"strategies":[69],"play":[71],"Atari":[72,211],"games":[73],"such":[74],"as":[75],"Breakout":[76,212],"Space":[78],"invaders.":[79],"Although":[80],"powerful":[81],"is":[84],"limited":[85],"actions.":[88,107,131],"If":[89],"we":[90,99,111,172],"wish":[91],"more":[94],"systems":[96,137],"like":[97],"robots":[98],"need":[100],"ability":[102,126],"output":[104,128],"multidimensional":[105,129],"continuous":[106,130],"In":[108],"this":[109,134],"paper":[110],"investigate":[112],"how":[113],"combine":[115],"actor":[120,139,163,176,185],"critic":[121,140,165,177,187],"models":[122],"which":[123,171],"We":[132,148,159,180,194],"name":[133,173],"class":[135],"(DACN)":[142],"following":[143],"DQN":[145],"naming":[146],"convention.":[147],"derive":[149],"experiment":[151],"four":[153],"methods":[154],"update":[156],"actor.":[158],"then":[160],"consolidate":[161],"into":[167],"one":[168],"unified":[169],"network":[170],"consolidated":[174],"(C-DACN).":[179],"hypothesize":[181],"consolidating":[183],"might":[189],"lead":[190],"faster":[192],"convergence.":[193],"test":[195],"two":[199],"environments":[200],"named":[201],"Acrobot":[202],"(under":[203],"actuated":[204],"double":[205],"pendulum)":[206],"Bounce":[208],"(continuous":[209],"action":[210],"look":[213],"alike).":[214]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}
