{"id":"https://openalex.org/W2977334489","doi":"https://doi.org/10.1109/devlrn.2019.8850693","title":"Looking Back and Ahead: Adaptation and Planning by Gradient Descent","display_name":"Looking Back and Ahead: Adaptation and Planning by Gradient Descent","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2977334489","doi":"https://doi.org/10.1109/devlrn.2019.8850693","mag":"2977334489"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2019.8850693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"},"type":"article","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/A5101663686","display_name":"Shingo Murata","orcid":"https://orcid.org/0000-0002-0790-1915"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shingo Murata","raw_affiliation_strings":["Principles of Informatics Research Division, National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Principles of Informatics Research Division, National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075032185","display_name":"Hiroki Sawa","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Sawa","raw_affiliation_strings":["Department of Modern Mechanical Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Modern Mechanical Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080654277","display_name":"Shigeki Sugano","orcid":"https://orcid.org/0000-0002-9331-2446"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Sugano","raw_affiliation_strings":["Department of Modern Mechanical Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Modern Mechanical Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ogata","raw_affiliation_strings":["Department of Intermedia Art and Science, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Intermedia Art and Science, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101663686"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12583753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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/T11883","display_name":"Embodied and Extended Cognition","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11883","display_name":"Embodied and Extended Cognition","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9715999960899353,"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/computer-science","display_name":"Computer science","score":0.6951591968536377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6782534718513489},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.675475537776947},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6652538180351257},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.6612297892570496},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5526710152626038},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.48612332344055176},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.48417928814888},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47910216450691223},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47765958309173584},{"id":"https://openalex.org/keywords/cma-es","display_name":"CMA-ES","score":0.4775729477405548},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4484371244907379},{"id":"https://openalex.org/keywords/automated-planning-and-scheduling","display_name":"Automated planning and scheduling","score":0.4223252534866333},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4132997691631317},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.41308680176734924},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34291893243789673},{"id":"https://openalex.org/keywords/evolution-strategy","display_name":"Evolution strategy","score":0.27149802446365356},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11418452858924866},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.111541748046875},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.09064269065856934},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0821121335029602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6951591968536377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6782534718513489},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.675475537776947},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6652538180351257},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6612297892570496},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5526710152626038},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.48612332344055176},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.48417928814888},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47910216450691223},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47765958309173584},{"id":"https://openalex.org/C205555498","wikidata":"https://www.wikidata.org/wiki/Q505588","display_name":"CMA-ES","level":4,"score":0.4775729477405548},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4484371244907379},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.4223252534866333},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4132997691631317},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.41308680176734924},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34291893243789673},{"id":"https://openalex.org/C207002847","wikidata":"https://www.wikidata.org/wiki/Q2912857","display_name":"Evolution strategy","level":3,"score":0.27149802446365356},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11418452858924866},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.111541748046875},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.09064269065856934},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0821121335029602},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2019.8850693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W149630149","https://openalex.org/W2025412857","https://openalex.org/W2059156134","https://openalex.org/W2059320470","https://openalex.org/W2089029564","https://openalex.org/W2094342172","https://openalex.org/W2119885245","https://openalex.org/W2132003317","https://openalex.org/W2137411342","https://openalex.org/W2148764920","https://openalex.org/W2153791616","https://openalex.org/W2157445228","https://openalex.org/W2345211079","https://openalex.org/W2586593146","https://openalex.org/W2594533284","https://openalex.org/W2765401264","https://openalex.org/W2795756076","https://openalex.org/W2897056651","https://openalex.org/W2901254592","https://openalex.org/W4297672196","https://openalex.org/W6606039115","https://openalex.org/W6683182819"],"related_works":["https://openalex.org/W11023528","https://openalex.org/W2235786","https://openalex.org/W6093035","https://openalex.org/W1354071","https://openalex.org/W11991885","https://openalex.org/W2683128","https://openalex.org/W11144228","https://openalex.org/W592020","https://openalex.org/W4911910","https://openalex.org/W12582432"],"abstract_inverted_index":{"Adaptation":[0],"and":[1,8,32,51,69,129],"planning":[2,33,163],"are":[3],"crucial":[4],"for":[5,49,103,112],"both":[6],"biological":[7],"artificial":[9],"agents.":[10],"In":[11],"this":[12],"study,":[13],"we":[14,22],"treat":[15],"these":[16,99],"as":[17],"an":[18],"inference":[19],"problem":[20],"that":[21,144],"solve":[23],"using":[24],"a":[25,38,43,126,133,138,146],"gradient-based":[26,39],"optimization":[27],"approach.":[28],"We":[29],"propose":[30],"adaptation":[31,50,109],"by":[34,59,70],"gradient":[35],"descent":[36],"(APGraDe),":[37],"computational":[40],"framework":[41,54,122],"with":[42,137],"hierarchical":[44],"recurrent":[45],"neural":[46],"network":[47],"(RNN)":[48],"planning.":[52,118],"This":[53],"computes":[55],"(counterfactual)":[56],"prediction":[57],"errors":[58,102,111],"looking":[60,71],"back":[61],"on":[62,66,77],"past":[63,105],"situations":[64,75,155],"based":[65,76],"actual":[67],"observations":[68,79],"ahead":[72],"to":[73,107,116,153],"future":[74,114,165],"preferred":[78],"(or":[80],"goal).":[81],"The":[82,101,119],"internal":[83],"state":[84],"of":[85,89,97,164],"the":[86,90,95,104,108,113,117,130,149,162],"higher":[87],"level":[88],"RNN":[91],"is":[92,123],"optimized":[93],"in":[94,125],"direction":[96],"minimizing":[98],"errors.":[100],"contribute":[106,115],"while":[110,156],"proposed":[120],"APGraDe":[121],"implemented":[124],"humanoid":[127],"robot":[128,131,150],"performs":[132],"ball":[134],"manipulation":[135],"task":[136],"human":[139],"experimenter.":[140],"Experimental":[141],"results":[142],"show":[143],"given":[145],"particular":[147],"preference,":[148],"can":[151],"adapt":[152],"unexpected":[154],"pursuing":[157],"its":[158],"own":[159],"preference":[160],"through":[161],"actions.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}