{"id":"https://openalex.org/W3207649131","doi":"https://doi.org/10.1109/icra48506.2021.9561891","title":"Learning Dense Rewards for Contact-Rich Manipulation Tasks","display_name":"Learning Dense Rewards for Contact-Rich Manipulation Tasks","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3207649131","doi":"https://doi.org/10.1109/icra48506.2021.9561891","mag":"3207649131"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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/A5071709906","display_name":"Zheng Wu","orcid":"https://orcid.org/0000-0002-2563-3387"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Wu","raw_affiliation_strings":["X, the Moonshot Factory,Mountain View,CA,USA,94043","University of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X, the Moonshot Factory,Mountain View,CA,USA,94043","institution_ids":[]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017678179","display_name":"Wenzhao Lian","orcid":"https://orcid.org/0000-0002-0995-8229"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenzhao Lian","raw_affiliation_strings":["X, the Moonshot Factory,Mountain View,CA,USA,94043"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X, the Moonshot Factory,Mountain View,CA,USA,94043","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012176895","display_name":"Vaibhav Unhelkar","orcid":"https://orcid.org/0000-0002-4530-189X"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhav Unhelkar","raw_affiliation_strings":["Rice University,Houston,TX,USA,77005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University,Houston,TX,USA,77005","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064077634","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masayoshi Tomizuka","raw_affiliation_strings":["University of California, Berkeley,Berkeley,CA,USA,94704"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley,Berkeley,CA,USA,94704","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029642293","display_name":"Stefan Schaal","orcid":"https://orcid.org/0000-0001-5660-1874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Schaal","raw_affiliation_strings":["X, the Moonshot Factory,Mountain View,CA,USA,94043"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X, the Moonshot Factory,Mountain View,CA,USA,94043","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6214","last_page":"6221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991999864578247,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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/T10338","display_name":"Advanced Sensor and Energy Harvesting Materials","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/computer-science","display_name":"Computer science","score":0.7796827554702759},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7764998078346252},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7610409259796143},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5364018082618713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5251909494400024},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49489253759384155},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47774213552474976},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.455961674451828},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40416407585144043},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4028635025024414},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09568619728088379}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7796827554702759},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7764998078346252},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7610409259796143},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5364018082618713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5251909494400024},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49489253759384155},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47774213552474976},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.455961674451828},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40416407585144043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4028635025024414},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09568619728088379},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/icra48506.2021.9561891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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":82,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W88368075","https://openalex.org/W1522301498","https://openalex.org/W1527702126","https://openalex.org/W1540685400","https://openalex.org/W1591675293","https://openalex.org/W1986014385","https://openalex.org/W1994648061","https://openalex.org/W1999874108","https://openalex.org/W2053910308","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2099471712","https://openalex.org/W2100235553","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2169498096","https://openalex.org/W2171302338","https://openalex.org/W2290104316","https://openalex.org/W2296055201","https://openalex.org/W2462906003","https://openalex.org/W2519091744","https://openalex.org/W2592535843","https://openalex.org/W2737215407","https://openalex.org/W2769112066","https://openalex.org/W2781726626","https://openalex.org/W2785962646","https://openalex.org/W2806130867","https://openalex.org/W2903158431","https://openalex.org/W2912997088","https://openalex.org/W2938421504","https://openalex.org/W2945023859","https://openalex.org/W2949382160","https://openalex.org/W2950102663","https://openalex.org/W2962679776","https://openalex.org/W2963277051","https://openalex.org/W2963311874","https://openalex.org/W2963373786","https://openalex.org/W2963484919","https://openalex.org/W2963508354","https://openalex.org/W2963516265","https://openalex.org/W2963590100","https://openalex.org/W2963629498","https://openalex.org/W2963646405","https://openalex.org/W2963713397","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W2967936796","https://openalex.org/W2968095426","https://openalex.org/W2972981152","https://openalex.org/W2995634437","https://openalex.org/W3000439273","https://openalex.org/W3003629310","https://openalex.org/W3004815632","https://openalex.org/W3037606473","https://openalex.org/W3040490156","https://openalex.org/W3090600213","https://openalex.org/W3091677803","https://openalex.org/W4211133235","https://openalex.org/W4298023569","https://openalex.org/W4320013936","https://openalex.org/W6603524897","https://openalex.org/W6631190155","https://openalex.org/W6632235069","https://openalex.org/W6635261211","https://openalex.org/W6674884181","https://openalex.org/W6682849425","https://openalex.org/W6696380822","https://openalex.org/W6718092244","https://openalex.org/W6718379498","https://openalex.org/W6718836005","https://openalex.org/W6741302124","https://openalex.org/W6745347688","https://openalex.org/W6747473740","https://openalex.org/W6752338937","https://openalex.org/W6755437240","https://openalex.org/W6756615331","https://openalex.org/W6762387550","https://openalex.org/W6767425681","https://openalex.org/W6773930613"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W2482350142","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W2768698792","https://openalex.org/W3213722473"],"abstract_inverted_index":{"Rewards":[0],"play":[1],"a":[2,17,104],"crucial":[3],"role":[4],"in":[5,38,103],"reinforcement":[6],"learning.":[7],"To":[8],"arrive":[9],"at":[10],"the":[11,14,35,90,109,131,135,147],"desired":[12],"policy,":[13],"design":[15],"of":[16,53,113],"suitable":[18],"reward":[19,40,56,74,137],"function":[20,138],"often":[21],"requires":[22],"significant":[23],"domain":[24],"expertise":[25],"as":[26,28,64],"well":[27],"trial-and-error.":[29],"Here,":[30],"we":[31,48],"aim":[32],"to":[33,71,89,146],"minimize":[34],"effort":[36],"involved":[37],"designing":[39],"functions":[41,57],"for":[42],"contact-rich":[43,118],"manipulation":[44,119],"tasks.":[45],"In":[46,69],"particular,":[47],"provide":[49],"an":[50],"approach":[51,78,96,115],"capable":[52],"extracting":[54],"dense":[55],"algorithmically":[58],"from":[59],"robots’":[60],"high-dimensional":[61,73],"observations,":[62],"such":[63],"images":[65],"and":[66,84,111,123,142],"tactile":[67],"feedback.":[68],"contrast":[70],"state-of-the-art":[72],"learning":[75],"methodologies,":[76],"our":[77,95,114],"does":[79],"not":[80],"leverage":[81],"adversarial":[82],"training,":[83],"is":[85],"thus":[86],"less":[87],"prone":[88],"associated":[91],"training":[92],"instabilities.":[93],"Instead,":[94],"learns":[97],"rewards":[98],"by":[99],"estimating":[100],"task":[101],"progress":[102],"self-supervised":[105],"manner.":[106],"We":[107],"demonstrate":[108],"effectiveness":[110],"efficiency":[112],"on":[116],"two":[117],"tasks,":[120],"namely,":[121],"peg-in-hole":[122],"USB":[124],"insertion.":[125],"The":[126],"experimental":[127],"results":[128],"indicate":[129],"that":[130],"policies":[132],"trained":[133],"with":[134],"learned":[136],"achieves":[139],"better":[140],"performance":[141],"faster":[143],"convergence":[144],"compared":[145],"baselines.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}