{"id":"https://openalex.org/W3015304759","doi":"https://doi.org/10.48550/arxiv.2004.04574","title":"Model-based actor-critic: GAN (model generator) + DRL (actor-critic) => AGI","display_name":"Model-based actor-critic: GAN (model generator) + DRL (actor-critic) => AGI","publication_year":2020,"publication_date":"2020-04-04","ids":{"openalex":"https://openalex.org/W3015304759","doi":"https://doi.org/10.48550/arxiv.2004.04574","mag":"3015304759"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2004.04574","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.04574","pdf_url":"https://arxiv.org/pdf/2004.04574","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.04574","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102776490","display_name":"Aras R. Dargazany","orcid":"https://orcid.org/0000-0002-7268-0434","observed_orcids":["https://orcid.org/0000-0002-7268-0434"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dargazany, Aras","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5102776490"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gan","display_name":"GaN","score":0.5529999732971191},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8870000243186951},{"id":"https://openalex.org/keywords/artificial-general-intelligence","display_name":"artificial general intelligence","score":0.8130000233650208},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.7649999856948853},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"episodic memory","score":0.9729999899864197},{"id":"https://openalex.org/keywords/robot-control","display_name":"robot control","score":0.5600000023841858},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.5070000290870667},{"id":"https://openalex.org/keywords/offline-learning","display_name":"offline learning","score":0.6570000052452087}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6855937242507935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.677994966506958},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5689687728881836},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5656223297119141},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5525845289230347},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5107031464576721},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4865640699863434},{"id":"https://openalex.org/C162027153","wikidata":"https://www.wikidata.org/wiki/Q2264109","display_name":"Artificial general intelligence","level":2,"score":0.4449632465839386},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.42318540811538696},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4132278561592102},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35301992297172546},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.28887423872947693},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15094256401062012},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.10872405767440796},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2004.04574","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.04574","pdf_url":"https://arxiv.org/pdf/2004.04574","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3015304759","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.04574","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"mag:3121262220","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2004.04574","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2004.04574","doi":"https://doi.org/10.48550/arxiv.2004.04574","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.04574","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.04574","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.04574","pdf_url":"https://arxiv.org/pdf/2004.04574","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015304759.pdf","grobid_xml":"https://content.openalex.org/works/W3015304759.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W1583833196","https://openalex.org/W2009303086","https://openalex.org/W2010736788","https://openalex.org/W2012592267","https://openalex.org/W2024187681","https://openalex.org/W2047057213","https://openalex.org/W2057768335","https://openalex.org/W2099471712","https://openalex.org/W2100677568","https://openalex.org/W2108501770","https://openalex.org/W2108772579","https://openalex.org/W2115836980","https://openalex.org/W2124659975","https://openalex.org/W2129409567","https://openalex.org/W2137172397","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2163605009","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2184045248","https://openalex.org/W2231381271","https://openalex.org/W2261666310","https://openalex.org/W2263389157","https://openalex.org/W2424347275","https://openalex.org/W2432004435","https://openalex.org/W2527819024","https://openalex.org/W2530472562","https://openalex.org/W2552465644","https://openalex.org/W2554506842","https://openalex.org/W2583528914","https://openalex.org/W2586693486","https://openalex.org/W2593729559","https://openalex.org/W2599794180","https://openalex.org/W2626778328","https://openalex.org/W2739748921","https://openalex.org/W2781585732","https://openalex.org/W2795456585","https://openalex.org/W2798091161","https://openalex.org/W2798705390","https://openalex.org/W2890208753","https://openalex.org/W2891404388","https://openalex.org/W2900152462","https://openalex.org/W2901823958","https://openalex.org/W2909190397","https://openalex.org/W2918154744","https://openalex.org/W2919115771","https://openalex.org/W2936017220","https://openalex.org/W2938421504","https://openalex.org/W2949416428","https://openalex.org/W2950004691","https://openalex.org/W2957313411","https://openalex.org/W2958540581","https://openalex.org/W2960199099","https://openalex.org/W2960410483","https://openalex.org/W2963091558","https://openalex.org/W2963470893","https://openalex.org/W2964125581","https://openalex.org/W2966381234","https://openalex.org/W2966564143","https://openalex.org/W2978993681","https://openalex.org/W3006025420","https://openalex.org/W3127151792"],"related_works":["https://openalex.org/W4394657392","https://openalex.org/W2770487696","https://openalex.org/W2527819024","https://openalex.org/W4408062672","https://openalex.org/W4205089755","https://openalex.org/W7018364279","https://openalex.org/W3095751527","https://openalex.org/W7053159833","https://openalex.org/W7117550058","https://openalex.org/W4416818405"],"abstract_inverted_index":{"Our":[0,70,146,175],"effort":[1],"is":[2,73,103,178],"toward":[3],"unifying":[4,11],"GAN":[5,34,154],"and":[6,44,68,95,108,136,143,153,204,214],"DRL":[7,55,152,189],"algorithms":[8],"into":[9],"a":[10,87,128],"AI":[12,17,101,183,192,213],"model":[13,78,102,184],"(AGI":[14],"or":[15,18,51,65],"general-purpose":[16,24],"artificial":[19],"general":[20],"intelligence":[21],"which":[22,84],"has":[23],"applications":[25],"to:":[26,186],"(A)":[27,187],"offline":[28],"learning":[29,48,226],"(of":[30,49],"stored":[31],"data)":[32],"like":[33,54],"in":[35,56,86,140,155,159],"(un/semi-/fully-)SL":[36],"setting":[37,58],"such":[38,62],"as":[39,63],"big":[40],"data":[41],"analytics":[42],"(mining)":[43],"visualization;":[45],"(B)":[46,208],"online":[47],"real":[50],"simulated":[52,134],"devices)":[53],"RL":[57],"(with/out":[59],"environment":[60,77],"reward)":[61],"(real":[64],"simulated)":[66],"robotics":[67,215],"control;":[69],"core":[71],"proposal":[72],"adding":[74],"an":[75,96,160],"(generative/predictive)":[76],"to":[79,105,127,165,172,179,198],"the":[80,181,199,210,219,227],"actor-critic":[81,89,157],"(model-free)":[82,106,121,173],"architecture":[83,90],"results":[85,158],"model-based":[88,112,156,202],"with":[91,120,169,225],"temporal-differencing":[92],"(TD)":[93],"error":[94],"episodic":[97],"memory.":[98],"The":[99],"proposed":[100,182],"similar":[104,170],"DDPG":[107,122],"therefore":[109],"it's":[110],"called":[111],"DDPG.":[113,174],"To":[114],"evaluate":[115],"it,":[116],"we":[117],"compare":[118],"it":[119],"by":[123,193,217,230],"applying":[124],"them":[125],"both":[126],"variety":[129],"(wide":[130],"range)":[131],"of":[132,201,222],"independent":[133],"robotic":[135],"control":[137],"task":[138,168],"environments":[139],"OpenAI":[141],"Gym":[142],"Unity":[144],"Agents.":[145],"initial":[147],"limited":[148],"experiments":[149],"show":[150],"that":[151],"incremental":[161],"goal-driven":[162],"intellignce":[163],"required":[164],"solve":[166],"each":[167],"performance":[171,196],"future":[176],"focus":[177],"investigate":[180],"potential":[185],"unify":[188],"field":[190],"inside":[191],"producing":[194],"competitive":[195],"compared":[197],"best":[200],"(PlaNet)":[203],"model-free":[205],"(D4PG)":[206],"approaches;":[207],"bridge":[209],"gap":[211],"between":[212],"communities":[216],"solving":[218],"important":[220],"problem":[221],"reward":[223,228],"engineering":[224],"function":[229],"demonstration.":[231]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2020-04-17T00:00:00"}