{"id":"https://openalex.org/W3193866930","doi":"https://doi.org/10.1109/ro-man50785.2021.9515411","title":"Competitive physical interaction by reinforcement learning agents using intention estimation","display_name":"Competitive physical interaction by reinforcement learning agents using intention estimation","publication_year":2021,"publication_date":"2021-08-08","ids":{"openalex":"https://openalex.org/W3193866930","doi":"https://doi.org/10.1109/ro-man50785.2021.9515411","mag":"3193866930"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man50785.2021.9515411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man50785.2021.9515411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103994154","display_name":"Hiroki Noda","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Noda","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058960117","display_name":"Satoshi Nishikawa","orcid":"https://orcid.org/0000-0003-0905-8615"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nishikawa","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059653874","display_name":"Ryuma Niiyama","orcid":"https://orcid.org/0000-0002-9072-8251"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuma Niiyama","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010543059","display_name":"Yasuo Kuniyoshi","orcid":"https://orcid.org/0000-0001-8443-4161"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuo Kuniyoshi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"649","last_page":"656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9645000100135803,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.913100004196167,"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":0.843518078327179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6377019882202148},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.525938093662262},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5102357864379883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4417492151260376},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36058932542800903},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19581937789916992},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1643989086151123},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1511324942111969}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.843518078327179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6377019882202148},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.525938093662262},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5102357864379883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4417492151260376},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36058932542800903},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19581937789916992},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1643989086151123},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1511324942111969},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man50785.2021.9515411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man50785.2021.9515411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1562043419","display_name":"Ball sport partner robot using human anticipation skill","funder_award_id":"18K18087","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1959608418","https://openalex.org/W1999927553","https://openalex.org/W2023172481","https://openalex.org/W2075604446","https://openalex.org/W2156737235","https://openalex.org/W2158782408","https://openalex.org/W2159119161","https://openalex.org/W2257979135","https://openalex.org/W2291152989","https://openalex.org/W2574978968","https://openalex.org/W2588114174","https://openalex.org/W2736601468","https://openalex.org/W2758442112","https://openalex.org/W2762117857","https://openalex.org/W2775797419","https://openalex.org/W2788212683","https://openalex.org/W2803926500","https://openalex.org/W2894976951","https://openalex.org/W2904455790","https://openalex.org/W2904501997","https://openalex.org/W2912793366","https://openalex.org/W2949464762","https://openalex.org/W2962966033","https://openalex.org/W2963231791","https://openalex.org/W2963403868","https://openalex.org/W2964227312","https://openalex.org/W2964251366","https://openalex.org/W2973525135","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3004039022","https://openalex.org/W3105474110","https://openalex.org/W3118881636","https://openalex.org/W4287899365","https://openalex.org/W4297810554","https://openalex.org/W4299802797","https://openalex.org/W4385245566","https://openalex.org/W6640963894","https://openalex.org/W6683195989","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6745190604","https://openalex.org/W6748910126","https://openalex.org/W6751912414","https://openalex.org/W6755069753","https://openalex.org/W6759194994","https://openalex.org/W6763484891","https://openalex.org/W6767919266","https://openalex.org/W6772005887","https://openalex.org/W6773882092","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"The":[0],"physical":[1,102],"human\u2013robot":[2,15],"interaction":[3],"(pHRI)":[4],"research":[5],"field":[6],"is":[7],"expected":[8],"to":[9,11,83],"contribute":[10],"competitive":[12,104],"and":[13,41,72,103,108,134,158],"cooperative":[14],"tasks":[16],"that":[17,46,63,114,127,135],"involve":[18],"force":[19],"interactions.":[20],"However,":[21],"compared":[22],"with":[23],"human\u2013human":[24],"interactions,":[25],"current":[26],"pHRI":[27],"approaches":[28,33],"lack":[29],"tactical":[30],"considerations.":[31],"Current":[32],"do":[34,42],"not":[35,43],"estimate":[36],"intentions":[37],"from":[38],"human":[39],"behavior":[40,141],"select":[44],"policies":[45],"are":[47],"appropriate":[48],"for":[49,120],"the":[50,65,74,92,95,115,129,137,140,143,152,155],"opponent\u2019s":[51,66,156],"changing":[52,67],"policy.":[53,162],"For":[54],"this":[55],"reason,":[56],"we":[57,112],"propose":[58],"a":[59,78],"reinforcement":[60,96],"learning":[61,97],"model":[62],"estimates":[64,154],"policy":[68,76,121,133,157],"using":[69,99],"time-series":[70],"observations":[71],"expresses":[73],"agent\u2019s":[75,131],"in":[77,87],"common":[79],"latent":[80,116,125,146],"space,":[81],"referring":[82],"descriptions":[84],"of":[85,94,136,142],"tactics":[86],"open-skill":[88],"sports.":[89],"We":[90],"verify":[91],"performance":[93],"agent":[98,153],"two":[100],"novel":[101],"environments,":[105],"push-hand":[106],"game":[107],"air-hockey.":[109],"From":[110],"this,":[111],"confirm":[113],"space":[117],"works":[118],"properly":[119],"information":[122],"because":[123],"each":[124],"variable":[126],"represents":[128],"machine":[130],"own":[132,161],"opponent":[138],"affects":[139],"agent.":[144],"Two":[145],"variables":[147],"can":[148],"clearly":[149],"express":[150],"how":[151],"decides":[159],"its":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}