{"id":"https://openalex.org/W2914987759","doi":"https://doi.org/10.1109/rcar.2018.8621776","title":"Towards High Level Skill Learning: Learn to Return Table Tennis Ball Using Monte-Carlo Based Policy Gradient Method","display_name":"Towards High Level Skill Learning: Learn to Return Table Tennis Ball Using Monte-Carlo Based Policy Gradient Method","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2914987759","doi":"https://doi.org/10.1109/rcar.2018.8621776","mag":"2914987759"},"language":"en","primary_location":{"id":"doi:10.1109/rcar.2018.8621776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar.2018.8621776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Real-time Computing and Robotics (RCAR)","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/A5101638641","display_name":"Yifeng Zhu","orcid":"https://orcid.org/0000-0002-2290-1411"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifeng Zhu","raw_affiliation_strings":["Zhejiang University, State Key Laboratory of Industrial Control and Technology, Hangzhou, 310027, P. R. China","State Key Laboratory of Industrial Control and Technology, Zhejiang University, Hangzhou, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, State Key Laboratory of Industrial Control and Technology, Hangzhou, 310027, P. R. China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"State Key Laboratory of Industrial Control and Technology, Zhejiang University, Hangzhou, P. R. China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119247322","display_name":"Yongsheng Zhao","orcid":"https://orcid.org/0009-0001-9355-0890"},"institutions":[{"id":"https://openalex.org/I186691195","display_name":"Qingdao Binhai University","ror":"https://ror.org/023er3e86","country_code":"CN","type":"education","lineage":["https://openalex.org/I186691195"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongsheng Zhao","raw_affiliation_strings":["Binhai Industrial Technology Research Institute of Zhejiang University, Tian, 300457, P. R. China","Binhai Industrial Technology Research Institute of Zhejiang University, Tian, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binhai Industrial Technology Research Institute of Zhejiang University, Tian, 300457, P. R. China","institution_ids":["https://openalex.org/I186691195"]},{"raw_affiliation_string":"Binhai Industrial Technology Research Institute of Zhejiang University, Tian, P. R. China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061317219","display_name":"Lisen Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lisen Jin","raw_affiliation_strings":["Zhejiang University, State Key Laboratory of Industrial Control and Technology, Hangzhou, 310027, P. R. China","State Key Laboratory of Industrial Control and Technology, Zhejiang University, Hangzhou, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, State Key Laboratory of Industrial Control and Technology, Hangzhou, 310027, P. R. China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"State Key Laboratory of Industrial Control and Technology, Zhejiang University, Hangzhou, P. R. China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021284542","display_name":"Jun Wu","orcid":"https://orcid.org/0000-0002-1388-7451"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wu","raw_affiliation_strings":["Zhejiang University, State Key Laboratory of Industrial Control and Technology, Hangzhou, 310027, P. R. China","State Key Laboratory of Industrial Control and Technology, Zhejiang University, Hangzhou, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, State Key Laboratory of Industrial Control and Technology, Hangzhou, 310027, P. R. China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"State Key Laboratory of Industrial Control and Technology, Zhejiang University, Hangzhou, P. R. China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019081110","display_name":"Rong Xiong","orcid":"https://orcid.org/0000-0001-9318-9014"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Xiong","raw_affiliation_strings":["Zhejiang University, State Key Laboratory of Industrial Control and Technology, Hangzhou, 310027, P. R. China","State Key Laboratory of Industrial Control and Technology, Zhejiang University, Hangzhou, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, State Key Laboratory of Industrial Control and Technology, Hangzhou, 310027, P. R. China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"State Key Laboratory of Industrial Control and Technology, Zhejiang University, Hangzhou, P. R. China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7923,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.78818364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"41"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7672762870788574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6763886213302612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6464148759841919},{"id":"https://openalex.org/keywords/ball","display_name":"Ball (mathematics)","score":0.6330598592758179},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6271081566810608},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4779796004295349},{"id":"https://openalex.org/keywords/tennis-ball","display_name":"Tennis ball","score":0.44028499722480774},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.41818124055862427},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3597579002380371},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3456918001174927},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18092450499534607},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12637609243392944}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7672762870788574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6763886213302612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6464148759841919},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.6330598592758179},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6271081566810608},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4779796004295349},{"id":"https://openalex.org/C2992174615","wikidata":"https://www.wikidata.org/wiki/Q246514","display_name":"Tennis ball","level":3,"score":0.44028499722480774},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.41818124055862427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3597579002380371},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3456918001174927},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18092450499534607},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12637609243392944},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2780101202","wikidata":"https://www.wikidata.org/wiki/Q768186","display_name":"sports equipment","level":2,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rcar.2018.8621776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar.2018.8621776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Real-time Computing and Robotics (RCAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W204153720","https://openalex.org/W1777239053","https://openalex.org/W2012204020","https://openalex.org/W2059698169","https://openalex.org/W2111978237","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2142300342","https://openalex.org/W2144576818","https://openalex.org/W2145339207","https://openalex.org/W2149860990","https://openalex.org/W2156737235","https://openalex.org/W2165150801","https://openalex.org/W2172968643","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2385601253","https://openalex.org/W2443711627","https://openalex.org/W2575705757","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W4214717370","https://openalex.org/W4237733001","https://openalex.org/W4302570325","https://openalex.org/W6638088447","https://openalex.org/W6682093400","https://openalex.org/W6683195989","https://openalex.org/W6684205842","https://openalex.org/W6692846177"],"related_works":["https://openalex.org/W2500432627","https://openalex.org/W2337502480","https://openalex.org/W2898907573","https://openalex.org/W2302011901","https://openalex.org/W2085868700","https://openalex.org/W2973156926","https://openalex.org/W2383982173","https://openalex.org/W2317418221","https://openalex.org/W584172674","https://openalex.org/W1988727730"],"abstract_inverted_index":{"Deep":[0,175],"learning":[1,52,92,169],"has":[2],"achieved":[3],"a":[4,38,42,47,96,101,104,112,118,122,151,158,165,202,237],"great":[5],"success":[6],"in":[7,29,80,107,137,171,184],"both":[8,81,236],"visual":[9],"and":[10,13,65,70,84,163,188,206,240],"acoustic":[11],"recognition":[12],"classification":[14],"tasks.":[15,193],"The":[16,194,219],"accuracy":[17],"of":[18,25,32,75,134,153,174,231],"many":[19],"state-of-the-art":[20],"methods":[21,93],"have":[22],"surpassed":[23],"that":[24,223],"human":[26,56,142],"beings.":[27],"However,":[28],"the":[30,60,131,135,172,207,224],"field":[31],"robotics,":[33],"it":[34,190],"remains":[35],"to":[36,45,68,99,103,126,198,201,211,214,235],"be":[37,117],"big":[39],"challenge":[40],"for":[41],"real":[43],"robot":[44,97,123],"master":[46],"high-level":[48],"skill":[49,156],"using":[50],"deep":[51],"methods,":[53],"even":[54],"though":[55],"can":[57,124,227],"easily":[58],"learn":[59,98,125],"task":[61],"from":[62],"demonstration,":[63],"imitation":[64],"practice.":[66],"Compared":[67],"Go":[69],"Atari":[71],"games,":[72],"this":[73,138,146,182],"kind":[74,152],"tasks":[76],"is":[77,110,197,210],"usually":[78],"continuous":[79],"state":[82,234],"space":[83],"action":[85],"space,":[86],"which":[87],"makes":[88],"value":[89],"based":[90,167],"reinforcement":[91,168],"unavailable.":[94],"Making":[95],"return":[100,199,212,229],"ball":[102],"desired":[105,203],"point":[106,204,239],"table":[108,128,186],"tennis":[109,129,187],"such":[111,150],"typical":[113],"task.":[114],"It":[115],"would":[116],"promising":[119],"step":[120],"if":[121],"play":[127],"without":[130],"exact":[132],"knowledge":[133],"models":[136],"sport":[139],"just":[140],"as":[141],"players":[143],"do.":[144],"In":[145],"paper,":[147],"we":[148,180],"consider":[149],"motion":[154,233],"decision":[155,160],"learning,":[157],"one-step":[159],"making":[161],"process,":[162],"give":[164],"Monte-Carlo":[166],"method":[170,183],"framework":[173],"Deterministic":[176],"Policy":[177],"Gradient.":[178],"Then":[179],"apply":[181],"robotic":[185],"test":[189],"on":[191],"two":[192],"first":[195],"one":[196,209],"balls":[200,213,230],"first,":[205],"second":[208],"randomly":[215,241],"selected":[216,242],"landing":[217,243],"points.":[218],"experimental":[220],"results":[221],"demonstrate":[222],"trained":[225],"policy":[226],"successfully":[228],"random":[232],"designated":[238],"points":[244],"with":[245],"high":[246],"accuracy.":[247]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}