{"id":"https://openalex.org/W2943584704","doi":"https://doi.org/10.1109/icassp40776.2020.9053221","title":"From Video Game to Real Robot: The Transfer Between Action Spaces","display_name":"From Video Game to Real Robot: The Transfer Between Action Spaces","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2943584704","doi":"https://doi.org/10.1109/icassp40776.2020.9053221","mag":"2943584704"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.00741","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000669498","display_name":"Janne Karttunen","orcid":null},"institutions":[{"id":"https://openalex.org/I3132474087","display_name":"Karelia University of Applied Sciences","ror":"https://ror.org/00db2vc28","country_code":"FI","type":"education","lineage":["https://openalex.org/I3132474087"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Janne Karttunen","raw_affiliation_strings":["Karelics Oy, Joensuu, Finland","Karelics Oy,Joensuu,Finland"],"affiliations":[{"raw_affiliation_string":"Karelics Oy, Joensuu, Finland","institution_ids":["https://openalex.org/I3132474087"]},{"raw_affiliation_string":"Karelics Oy,Joensuu,Finland","institution_ids":["https://openalex.org/I3132474087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048689678","display_name":"Anssi Kanervisto","orcid":"https://orcid.org/0000-0002-7479-4574"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Anssi Kanervisto","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Joensuu, Finland","[University of Eastern Finland, School of Computing, Joensuu, Finland]"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"[University of Eastern Finland, School of Computing, Joensuu, Finland]","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080940147","display_name":"Ville Kyrki","orcid":"https://orcid.org/0000-0002-5230-5549"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Kyrki","raw_affiliation_strings":["School of Electrical Engineering, Aalto University, Espoo, Finland","Aalto University School of Electrical Engineering,,,Espoo,,Finland"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University School of Electrical Engineering,,,Espoo,,Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Hautamaki","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Joensuu, Finland","[University of Eastern Finland, School of Computing, Joensuu, Finland]"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"[University of Eastern Finland, School of Computing, Joensuu, Finland]","institution_ids":["https://openalex.org/I175532246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000669498"],"corresponding_institution_ids":["https://openalex.org/I3132474087"],"apc_list":null,"apc_paid":null,"fwci":0.1372,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51897736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 1703 472","issue":null,"first_page":"3567","last_page":"3571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/action","display_name":"Action (physics)","score":0.7239975333213806},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7114283442497253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995744109153748},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6893913745880127},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6519194841384888},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.6032808423042297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5587853193283081},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5520369410514832},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5370373725891113},{"id":"https://openalex.org/keywords/video-game","display_name":"Video game","score":0.45643460750579834},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4462524354457855},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4456605315208435},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.327390193939209},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2863790988922119},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08232304453849792}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7239975333213806},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7114283442497253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995744109153748},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6893913745880127},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6519194841384888},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.6032808423042297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5587853193283081},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5520369410514832},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5370373725891113},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.45643460750579834},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4462524354457855},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4456605315208435},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.327390193939209},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2863790988922119},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08232304453849792},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.00741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.00741","pdf_url":"https://arxiv.org/pdf/1905.00741","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":"","raw_type":"text"},{"id":"mag:2943584704","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1905.00741.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1905.00741","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.00741","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/8fmw-wb04","is_oa":true,"landing_page_url":"https://doi.org/10.17023/8fmw-wb04","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.00741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.00741","pdf_url":"https://arxiv.org/pdf/1905.00741","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2943584704.pdf","grobid_xml":"https://content.openalex.org/works/W2943584704.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1512137381","https://openalex.org/W2097381042","https://openalex.org/W2113839990","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2362143032","https://openalex.org/W2426267443","https://openalex.org/W2547416798","https://openalex.org/W2591697182","https://openalex.org/W2592873849","https://openalex.org/W2605102758","https://openalex.org/W2605368761","https://openalex.org/W2615547864","https://openalex.org/W2736601468","https://openalex.org/W2749807327","https://openalex.org/W2883192382","https://openalex.org/W2885163910","https://openalex.org/W2911087563","https://openalex.org/W2963184939","https://openalex.org/W2963864421","https://openalex.org/W2963871073","https://openalex.org/W2964043796","https://openalex.org/W3103780890","https://openalex.org/W6674600207","https://openalex.org/W6677258307","https://openalex.org/W6685444567","https://openalex.org/W6728881815","https://openalex.org/W6734065107","https://openalex.org/W6741002519","https://openalex.org/W6743756900","https://openalex.org/W6753003069","https://openalex.org/W6770858630","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W3015212932","https://openalex.org/W2114882146","https://openalex.org/W2959349500","https://openalex.org/W2910384675","https://openalex.org/W2972127687","https://openalex.org/W2810723160","https://openalex.org/W2159377235","https://openalex.org/W2008386664","https://openalex.org/W3183112146","https://openalex.org/W153292794","https://openalex.org/W1884601587","https://openalex.org/W2909112693","https://openalex.org/W2804727265","https://openalex.org/W3009295642","https://openalex.org/W3208116419","https://openalex.org/W904535523","https://openalex.org/W2741177894","https://openalex.org/W3046125856","https://openalex.org/W2421136984","https://openalex.org/W2792089292"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,9,36],"has":[3],"proven":[4],"to":[5,40,53,75],"be":[6,38,88,131],"successful":[7],"for":[8,18,95],"tasks":[10],"in":[11,20,45,148],"simulated":[12,47],"environments,":[13],"but":[14],"applying":[15],"same":[16],"techniques":[17],"robots":[19],"real-world":[21],"domain":[22],"is":[23],"more":[24],"challenging,":[25],"as":[26],"they":[27],"require":[28],"hours":[29],"of":[30,92,137],"training.":[31],"To":[32],"address":[33],"this,":[34],"transfer":[35,51],"can":[37,87,105,130],"used":[39,90],"train":[41],"the":[42,57,63,96,103,107,113,119,126],"policy":[43],"first":[44],"a":[46],"environment":[48],"and":[49,66,140,150],"then":[50],"it":[52],"physical":[54],"agent.":[55],"As":[56],"simulation":[58,149],"never":[59],"matches":[60],"reality":[61],"perfectly,":[62],"physics,":[64],"visuals":[65],"action":[67,109,128],"spaces":[68],"by":[69,133],"necessity":[70],"differ":[71],"between":[72],"these":[73],"environments":[74],"some":[76],"degree.":[77],"In":[78],"this":[79],"work,":[80],"we":[81,100,141],"study":[82,101],"how":[83,102],"general":[84],"video":[85],"games":[86],"directly":[89],"instead":[91],"fine-tuned":[93],"simulations":[94],"sim-to-real":[97],"transfer.":[98],"Especially,":[99],"agent":[104],"learn":[106],"new":[108],"space":[110,129],"autonomously,":[111],"when":[112],"game":[114],"actions":[115],"do":[116],"not":[117],"match":[118],"robot":[120,151],"actions.":[121],"Our":[122],"results":[123],"show":[124],"that":[125],"different":[127],"learned":[132],"re-training":[134],"only":[135],"part":[136],"neural":[138],"network":[139],"obtain":[142],"above":[143],"90%":[144],"mean":[145],"success":[146],"rate":[147],"experiments.":[152]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
