{"id":"https://openalex.org/W4312858429","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892464","title":"Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning","display_name":"Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312858429","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892464"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892464","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.13343","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055938823","display_name":"Rei Sato","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"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Rei Sato","raw_affiliation_strings":["Graduate School of Science and Technology, University of Tsukuba,Tsukuba,Japan","RIKEN Center for Advanced Intelligence Project","Graduate School of Science and Technology, University of Tsukuba, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Technology, University of Tsukuba,Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Graduate School of Science and Technology, University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008914720","display_name":"Kazuto Fukuchi","orcid":"https://orcid.org/0000-0003-3895-219X"},"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"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuto Fukuchi","raw_affiliation_strings":["University of Tsukuba,Faculty of Engineering, Information and Systems,Tsukuba,Japan","RIKEN Center for Advanced Intelligence Project","Faculty of Engineering, Information and Systems, University of Tsukuba, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Faculty of Engineering, Information and Systems,Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Faculty of Engineering, Information and Systems, University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022139141","display_name":"Jun Sakuma","orcid":"https://orcid.org/0000-0001-5015-3812"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"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":"Jun Sakuma","raw_affiliation_strings":["University of Tsukuba,Faculty of Engineering, Information and Systems,Tsukuba,Japan","RIKEN Center for Advanced Intelligence Project","Faculty of Engineering, Information and Systems, University of Tsukuba, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Faculty of Engineering, Information and Systems,Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Faculty of Engineering, Information and Systems, University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038757231","display_name":"Youhei Akimoto","orcid":"https://orcid.org/0000-0003-2760-8123"},"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"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Youhei Akimoto","raw_affiliation_strings":["University of Tsukuba,Faculty of Engineering, Information and Systems,Tsukuba,Japan","RIKEN Center for Advanced Intelligence Project","Faculty of Engineering, Information and Systems, University of Tsukuba, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Faculty of Engineering, Information and Systems,Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Faculty of Engineering, Information and Systems, University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055938823"],"corresponding_institution_ids":["https://openalex.org/I146399215","https://openalex.org/I4210126580"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17018232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"10"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9966999888420105,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9929999709129333,"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/interpretability","display_name":"Interpretability","score":0.8345822095870972},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7298252582550049},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.683927059173584},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6478356122970581},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6192284822463989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5851280093193054},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.5796297788619995},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5722720623016357},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.49086910486221313},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.41226693987846375},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4061397612094879},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3967127799987793},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11250543594360352}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8345822095870972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7298252582550049},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.683927059173584},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6478356122970581},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6192284822463989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5851280093193054},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.5796297788619995},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5722720623016357},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.49086910486221313},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.41226693987846375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4061397612094879},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3967127799987793},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11250543594360352},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892464","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2301.13343","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.13343","pdf_url":"https://arxiv.org/pdf/2301.13343","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.13343","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.13343","pdf_url":"https://arxiv.org/pdf/2301.13343","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312858429.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1959608418","https://openalex.org/W2593768305","https://openalex.org/W2605102758","https://openalex.org/W2736601468","https://openalex.org/W2737215781","https://openalex.org/W2781585732","https://openalex.org/W2788781499","https://openalex.org/W2799017078","https://openalex.org/W2808849637","https://openalex.org/W2810785043","https://openalex.org/W2890208753","https://openalex.org/W2900263002","https://openalex.org/W2910982074","https://openalex.org/W2962736495","https://openalex.org/W2962755824","https://openalex.org/W2962793481","https://openalex.org/W2962899390","https://openalex.org/W2963390419","https://openalex.org/W2963488340","https://openalex.org/W2963871073","https://openalex.org/W2964198579","https://openalex.org/W2969329576","https://openalex.org/W2986514296","https://openalex.org/W3009584650","https://openalex.org/W3030981716","https://openalex.org/W3035756007","https://openalex.org/W3092037789","https://openalex.org/W3102186490","https://openalex.org/W3115293622","https://openalex.org/W3121989526","https://openalex.org/W3177473017","https://openalex.org/W3206394619","https://openalex.org/W4288094554","https://openalex.org/W4297744728","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6734871034","https://openalex.org/W6741002519","https://openalex.org/W6741036684","https://openalex.org/W6741977017","https://openalex.org/W6747387971","https://openalex.org/W6748523217","https://openalex.org/W6752601656","https://openalex.org/W6753243525","https://openalex.org/W6754184789","https://openalex.org/W6755800473","https://openalex.org/W6758233323","https://openalex.org/W6768843968","https://openalex.org/W6774583691","https://openalex.org/W6775634482","https://openalex.org/W6780645806","https://openalex.org/W6785684253","https://openalex.org/W6786816963"],"related_works":["https://openalex.org/W2566406229","https://openalex.org/W3177930984","https://openalex.org/W2052697133","https://openalex.org/W2119028572","https://openalex.org/W2376984068","https://openalex.org/W2152482390","https://openalex.org/W2365617273","https://openalex.org/W2076896210","https://openalex.org/W2506386910","https://openalex.org/W2117928543"],"abstract_inverted_index":{"We":[0,146],"investigate":[1],"policy":[2,95,102],"transfer":[3,55,108],"using":[4,81],"image-to-semantics":[5,82,117],"translation":[6],"to":[7,51,62,72,92],"mitigate":[8],"learning":[9,47,116],"difficulties":[10],"in":[11,59,86,115,139,150,157],"vision-based":[12],"robotics":[13],"control":[14],"agents.":[15],"This":[16],"problem":[17],"assumes":[18],"two":[19,131],"environments:":[20],"a":[21,37,56,126,148,155],"simulator":[22,141],"environment":[23,39,142],"with":[24,40,135],"semantics,":[25,52],"that":[26],"is,":[27],"low-dimensional":[28],"and":[29,36,77,96,143,163],"essential":[30],"information,":[31],"as":[32,42],"the":[33,43,60,63,89,94,97,100,112,120,136,140,151,158,161,164,168],"state":[34,44],"space,":[35],"real-world":[38,68],"images":[41,50],"space.":[45],"By":[46],"mapping":[48,83],"from":[49],"we":[53,129],"can":[54],"policy,":[57],"pre-trained":[58],"simulator,":[61],"real":[64],"world,":[65],"thereby":[66],"eliminating":[67],"on-policy":[69],"agent":[70],"interactions":[71],"learn,":[73],"which":[74],"are":[75],"costly":[76],"risky.":[78],"In":[79],"addition,":[80],"is":[84],"advantageous":[85],"terms":[87],"of":[88,99,106,160],"computational":[90],"efficiency":[91],"train":[93],"interpretability":[98],"obtained":[101],"over":[103],"other":[104],"types":[105],"sim-to-real":[107],"strategies.":[109],"To":[110],"tackle":[111],"main":[113],"difficulty":[114],"mapping,":[118],"namely":[119],"human":[121],"annotation":[122,152],"cost":[123,153],"for":[124],"producing":[125],"training":[127],"dataset,":[128],"propose":[130],"techniques:":[132],"pair":[133],"augmentation":[134],"transition":[137],"function":[138],"active":[144],"learning.":[145],"observed":[147],"reduction":[149],"without":[154,171],"decline":[156],"performance":[159],"transfer,":[162],"proposed":[165],"approach":[166,170],"outperformed":[167],"existing":[169],"annotation.":[172]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}