{"id":"https://openalex.org/W3117178794","doi":"https://doi.org/10.1109/gcce50665.2020.9292009","title":"Discriminator Soft Actor Critic without Extrinsic Rewards","display_name":"Discriminator Soft Actor Critic without Extrinsic Rewards","publication_year":2020,"publication_date":"2020-10-13","ids":{"openalex":"https://openalex.org/W3117178794","doi":"https://doi.org/10.1109/gcce50665.2020.9292009","mag":"3117178794"},"language":"en","primary_location":{"id":"doi:10.1109/gcce50665.2020.9292009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce50665.2020.9292009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","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/A5046223937","display_name":"Daichi Nishio","orcid":null},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Daichi Nishio","raw_affiliation_strings":["Kanazawa University, Kanazawa, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Ishikawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000097788","display_name":"Toi Tsuneda","orcid":"https://orcid.org/0000-0003-1913-9179"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toi Tsuneda","raw_affiliation_strings":["Kanazawa University, Kanazawa, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Ishikawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083622472","display_name":"Daiki Kuyoshi","orcid":null},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daiki Kuyoshi","raw_affiliation_strings":["Kanazawa University, Kanazawa, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Ishikawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102728648","display_name":"Satoshi Yamane","orcid":"https://orcid.org/0000-0001-7883-4054"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Yamane","raw_affiliation_strings":["Kanazawa University, Kanazawa, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Ishikawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046223937"],"corresponding_institution_ids":["https://openalex.org/I10091056"],"apc_list":null,"apc_paid":null,"fwci":0.5302,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74006313,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 2001 6808","issue":null,"first_page":"117","last_page":"120"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9337000250816345,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9031999707221985,"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/discriminator","display_name":"Discriminator","score":0.9172099828720093},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7838464975357056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7353100776672363},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.692338764667511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5885633230209351},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5125653743743896},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5038115382194519},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.44787177443504333},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4158678352832794},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10107174515724182}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9172099828720093},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7838464975357056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353100776672363},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.692338764667511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5885633230209351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5125653743743896},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5038115382194519},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.44787177443504333},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4158678352832794},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10107174515724182},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce50665.2020.9292009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce50665.2020.9292009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2051228319","https://openalex.org/W2099471712","https://openalex.org/W2158782408","https://openalex.org/W2766610320","https://openalex.org/W2781726626","https://openalex.org/W2904246096","https://openalex.org/W2944911388","https://openalex.org/W2963508354","https://openalex.org/W2994240296","https://openalex.org/W3002890247","https://openalex.org/W3117178794","https://openalex.org/W3157836284","https://openalex.org/W4320013936","https://openalex.org/W6772712237"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W1914583973","https://openalex.org/W2130711276","https://openalex.org/W4308828368"],"abstract_inverted_index":{"In":[0,35],"environments":[1,72],"where":[2],"reward":[3,59],"design":[4],"is":[5,9,17],"difficult,":[6],"imitation":[7,19],"learning":[8,20],"often":[10],"used":[11],"rather":[12],"than":[13],"reinforcement":[14,64],"learning.":[15,65],"SQIL":[16,39],"an":[18],"algorithm":[21,56],"that":[22],"can":[23],"learn":[24],"with":[25],"little":[26],"expert":[27,77],"data":[28,31],"and":[29],"sample":[30],"from":[32],"the":[33],"environment.":[34],"order":[36],"to":[37,42],"make":[38],"more":[40],"robust":[41],"distributional":[43],"shifts,":[44],"in":[45,69],"this":[46],"paper,":[47],"we":[48],"propose":[49],"Discriminator":[50],"Soft":[51],"Actor":[52],"Critic":[53],"(DSAC).":[54],"The":[55],"uses":[57],"a":[58],"function":[60],"based":[61],"on":[62],"inverse":[63],"We":[66],"evaluate":[67],"it":[68],"continuous":[70],"control":[71],"by":[73],"4":[74],"episodes":[75],"of":[76],"data.":[78]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}