{"id":"https://openalex.org/W4302775009","doi":"https://doi.org/10.23919/sice56594.2022.9905810","title":"Disturbance Observable Reinforcement Learning that Compensates for Changes in Environment","display_name":"Disturbance Observable Reinforcement Learning that Compensates for Changes in Environment","publication_year":2022,"publication_date":"2022-09-06","ids":{"openalex":"https://openalex.org/W4302775009","doi":"https://doi.org/10.23919/sice56594.2022.9905810"},"language":"en","primary_location":{"id":"doi:10.23919/sice56594.2022.9905810","is_oa":false,"landing_page_url":"https://doi.org/10.23919/sice56594.2022.9905810","pdf_url":null,"source":{"id":"https://openalex.org/S4363608498","display_name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","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/A5068515235","display_name":"SeongIn Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"SeongIn Kim","raw_affiliation_strings":["University of Tsukuba,Master’s Program in Intelligent and Mechanical Interaction Systems,Ibaraki,Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Master’s Program in Intelligent and Mechanical Interaction Systems,Ibaraki,Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101693065","display_name":"Takeshi Shibuya","orcid":"https://orcid.org/0000-0003-4645-5898"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Shibuya","raw_affiliation_strings":["University of Tsukuba,Faculty of Engineering, Information and Systems,Ibaraki,Japan","Faculty of Engineering, Information and Systems, University of Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Faculty of Engineering, Information and Systems,Ibaraki,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"Faculty of Engineering, Information and Systems, University of Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068515235"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10881276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9807999730110168,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7607895135879517},{"id":"https://openalex.org/keywords/disturbance","display_name":"Disturbance (geology)","score":0.7388095259666443},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.7322989702224731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49595460295677185},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48267415165901184},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.39820006489753723},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.3422034978866577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30616694688796997},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.17503857612609863},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1594277322292328},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1059388816356659},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.07064005732536316},{"id":"https://openalex.org/keywords/paleontology","display_name":"Paleontology","score":0.06494680047035217}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7607895135879517},{"id":"https://openalex.org/C2777601987","wikidata":"https://www.wikidata.org/wiki/Q5283581","display_name":"Disturbance (geology)","level":2,"score":0.7388095259666443},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.7322989702224731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49595460295677185},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48267415165901184},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.39820006489753723},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.3422034978866577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30616694688796997},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.17503857612609863},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1594277322292328},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1059388816356659},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.07064005732536316},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.06494680047035217},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/sice56594.2022.9905810","is_oa":false,"landing_page_url":"https://doi.org/10.23919/sice56594.2022.9905810","pdf_url":null,"source":{"id":"https://openalex.org/S4363608498","display_name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2105078254","https://openalex.org/W2145339207","https://openalex.org/W2602963933","https://openalex.org/W2736601468","https://openalex.org/W2914994663","https://openalex.org/W3152878473","https://openalex.org/W3173921802","https://openalex.org/W6735677848","https://openalex.org/W6741002519","https://openalex.org/W6759312646","https://openalex.org/W6775359006"],"related_works":["https://openalex.org/W2038604956","https://openalex.org/W2296560746","https://openalex.org/W2338222801","https://openalex.org/W1994680671","https://openalex.org/W2347583731","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2000283393","https://openalex.org/W2920061524","https://openalex.org/W2002320543"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,42],"is":[2,51,76],"a":[3,98,125,139],"method":[4,134],"that":[5,83,132],"acquires":[6,43],"control":[7,22,45],"rules":[8,23,46],"by":[9],"interacting":[10],"with":[11,112],"the":[12,20,25,34,63,69,78,84,92,117,120],"system":[13],"dynamics\u2019":[14],"so-called":[15],"environment.":[16,57,80,143],"However,":[17],"when":[18],"applying":[19],"acquired":[21],"in":[24,33,77],"real":[26],"world,":[27],"tasks":[28],"fail":[29],"due":[30],"to":[31,61,71,104,115],"changes":[32],"environment":[35,87],"(e.g.,":[36],"friction":[37],"and":[38,67,109,128],"mass).":[39],"Since":[40],"reinforcement":[41],"optimal":[44,54],"under":[47,55,138],"train":[48],"environment,":[49],"it":[50,75,111],"no":[52],"longer":[53],"changed":[56,106],"Therefore,":[58],"we":[59,100],"propose":[60],"infer":[62,116],"change":[64,85,93,118],"of":[65,86,94,119],"dynamics":[66,103],"compensate":[68],"action":[70,108,114],"act":[72],"as":[73,91],"if":[74],"unchanged":[79],"We":[81],"show":[82],"can":[88],"be":[89],"seen":[90],"input":[95,107,113],"action.":[96],"As":[97],"result,":[99],"used":[101],"inverse":[102],"get":[105],"compared":[110],"dynamics.":[121],"Experiments":[122],"conducted":[123],"using":[124],"mass-spring":[126],"damping":[127],"pendulum":[129],"simulation":[130],"demonstrate":[131],"our":[133],"improves":[135],"task":[136],"performance":[137],"changing":[140],"affine":[141],"non-linear":[142]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}