{"id":"https://openalex.org/W4401751404","doi":"https://doi.org/10.1109/aim55361.2024.10637217","title":"Solving Challenging Tasks with Manipulation Policy with Limited Demonstrations","display_name":"Solving Challenging Tasks with Manipulation Policy with Limited Demonstrations","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4401751404","doi":"https://doi.org/10.1109/aim55361.2024.10637217"},"language":"en","primary_location":{"id":"doi:10.1109/aim55361.2024.10637217","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aim55361.2024.10637217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Intelligent Mechatronics (AIM)","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/A5054309906","display_name":"Haofeng Liu","orcid":"https://orcid.org/0009-0009-0320-3536"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Haofeng Liu","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024278773","display_name":"Jiayi Tan","orcid":"https://orcid.org/0000-0001-5938-7471"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiayi Tan","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109766956","display_name":"Yanchun Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yanchun Cheng","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439337","display_name":"Yiwen Chen","orcid":"https://orcid.org/0000-0003-0098-0531"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yiwen Chen","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070425949","display_name":"Haiyue Zhu","orcid":"https://orcid.org/0000-0002-3177-8195"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haiyue Zhu","raw_affiliation_strings":["Agency for Science, Technology and Research (A*STAR)"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research (A*STAR)","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064469965","display_name":"Marcelo H. Ang","orcid":"https://orcid.org/0000-0001-8277-6408"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Marcelo H Ang","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5054309906"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11409972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"697","last_page":"702"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12288","display_name":"Optimization and Search Problems","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9887999892234802,"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/computer-science","display_name":"Computer science","score":0.6734316349029541},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.364553302526474},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.32126760482788086},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16554880142211914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6734316349029541},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.364553302526474},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.32126760482788086},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16554880142211914}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aim55361.2024.10637217","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aim55361.2024.10637217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Intelligent Mechatronics (AIM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1997461667","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2575705757","https://openalex.org/W2741122588","https://openalex.org/W2904246096","https://openalex.org/W2947474832","https://openalex.org/W2963411833","https://openalex.org/W2963864421","https://openalex.org/W2990747716","https://openalex.org/W2991355586","https://openalex.org/W3009593063","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3037625705","https://openalex.org/W3089340499","https://openalex.org/W3169291081","https://openalex.org/W3172360140","https://openalex.org/W3203827806","https://openalex.org/W3205794883","https://openalex.org/W4287756699","https://openalex.org/W4288363736","https://openalex.org/W4300001294","https://openalex.org/W4391422971","https://openalex.org/W6634449904","https://openalex.org/W6640174482","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6712392314","https://openalex.org/W6742461812","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6757469721","https://openalex.org/W6761709163","https://openalex.org/W6768977950","https://openalex.org/W6771270455","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6779656125","https://openalex.org/W6780559895","https://openalex.org/W6783953388","https://openalex.org/W6796289742","https://openalex.org/W6796589144","https://openalex.org/W6801801719","https://openalex.org/W6802659552","https://openalex.org/W6851597212","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL),":[3],"combined":[4],"with":[5,33,149],"demonstration":[6,52,111],"data,":[7],"has":[8],"progressed":[9],"in":[10,45,54,141],"developing":[11],"manipulation":[12,46],"policies.":[13],"However,":[14],"the":[15,34,114,120,142],"practical":[16],"collection":[17],"of":[18,37,84,152],"ample":[19],"high-quality":[20],"demonstrations":[21,25,64,100,131,151],"is":[22],"timeconsuming,":[23],"and":[24,57,87,124,145],"generated":[26],"by":[27],"humans":[28],"may":[29],"not":[30],"perfectly":[31],"align":[32],"operational":[35],"demands":[36],"robots.":[38],"Our":[39],"study":[40],"suggests":[41],"that":[42],"RL":[43,67],"agents":[44],"tasks":[47],"are":[48],"acutely":[49],"sensitive":[50],"to":[51,65,101],"quality":[53],"both":[55],"online":[56],"offline":[58,115],"environments.":[59],"Utilizing":[60],"low-quality":[61],"or":[62],"limited":[63,150],"enhance":[66],"policy":[68,134],"development":[69],"remains":[70],"a":[71,93],"significant":[72],"challenge.":[73],"To":[74],"address":[75],"these":[76],"concerns,":[77],"we":[78],"propose":[79],"TD3+Smooth":[80,117],"BC,":[81],"an":[82],"enhancement":[83],"TD3+BC":[85],"[1]":[86],"TD3fG":[88],"[2].":[89],"This":[90],"algorithm":[91,137],"ensures":[92],"smooth":[94],"transition":[95],"from":[96,103],"learning":[97,102],"through":[98],"expert":[99],"experience,":[104],"incorporating":[105],"prior":[106],"knowledge":[107],"while":[108],"mitigating":[109],"negative":[110],"impacts.":[112],"In":[113],"setting,":[116],"BC":[118],"adjusts":[119],"balance":[121],"between":[122],"imitation":[123],"Q-value":[125],"maximization":[126],"dynamically,":[127],"effectively":[128],"utilizing":[129],"human":[130],"for":[132],"efficient":[133],"learning.":[135],"The":[136],"demonstrates":[138],"marked":[139],"improvements":[140],"Adroit":[143],"manipulator":[144],"MuJoCo":[146],"tasks,":[147],"even":[148],"varying":[153],"quality.":[154]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}