{"id":"https://openalex.org/W3206976301","doi":"https://doi.org/10.1109/icra48506.2021.9561927","title":"Reward Machines for Vision-Based Robotic Manipulation","display_name":"Reward Machines for Vision-Based Robotic Manipulation","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3206976301","doi":"https://doi.org/10.1109/icra48506.2021.9561927","mag":"3206976301"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561927","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":"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/A5001444744","display_name":"Alberto Rivas","orcid":"https://orcid.org/0000-0002-9558-9895"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alberto Camacho","raw_affiliation_strings":["Robotics at Google, New York"],"affiliations":[{"raw_affiliation_string":"Robotics at Google, New York","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081648393","display_name":"Jacob Varley","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Varley","raw_affiliation_strings":["Robotics at Google, New York"],"affiliations":[{"raw_affiliation_string":"Robotics at Google, New York","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005577303","display_name":"Andy Zeng","orcid":"https://orcid.org/0000-0002-4319-2159"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andy Zeng","raw_affiliation_strings":["Robotics at Google, New York"],"affiliations":[{"raw_affiliation_string":"Robotics at Google, New York","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041549191","display_name":"Deepali Jain","orcid":"https://orcid.org/0000-0001-9994-7584"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deepali Jain","raw_affiliation_strings":["Robotics at Google, New York"],"affiliations":[{"raw_affiliation_string":"Robotics at Google, New York","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015686392","display_name":"At\u0131l I\u015f\u00e7en","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atil Iscen","raw_affiliation_strings":["Robotics at Google, New York"],"affiliations":[{"raw_affiliation_string":"Robotics at Google, New York","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052190303","display_name":"Dmitry Kalashnikov","orcid":"https://orcid.org/0000-0002-8954-6178"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitry Kalashnikov","raw_affiliation_strings":["Robotics at Google, New York"],"affiliations":[{"raw_affiliation_string":"Robotics at Google, New York","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001444744"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.9425,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.86232273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"14284","last_page":"14290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9970999956130981,"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":0.9970999956130981,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.9884999990463257,"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":0.7753965854644775},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7338048219680786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6307380199432373},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5650078654289246},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5447800755500793},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5422123670578003},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5255338549613953},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.462318480014801},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4406786859035492},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4253350496292114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753965854644775},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7338048219680786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6307380199432373},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5650078654289246},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5447800755500793},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5422123670578003},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5255338549613953},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.462318480014801},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4406786859035492},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4253350496292114},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9561927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561927","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":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1903029394","https://openalex.org/W1999156278","https://openalex.org/W2058735307","https://openalex.org/W2088038240","https://openalex.org/W2109910161","https://openalex.org/W2145339207","https://openalex.org/W2194775991","https://openalex.org/W2284050935","https://openalex.org/W2397240726","https://openalex.org/W2468354762","https://openalex.org/W2626073992","https://openalex.org/W2734058336","https://openalex.org/W2741995169","https://openalex.org/W2785397276","https://openalex.org/W2804948070","https://openalex.org/W2806098286","https://openalex.org/W2810785043","https://openalex.org/W2900879308","https://openalex.org/W2902907165","https://openalex.org/W2904715276","https://openalex.org/W2914261249","https://openalex.org/W2962736495","https://openalex.org/W2962787403","https://openalex.org/W2962793652","https://openalex.org/W2963092423","https://openalex.org/W2963504932","https://openalex.org/W2963685250","https://openalex.org/W2964338130","https://openalex.org/W2966537673","https://openalex.org/W2970673985","https://openalex.org/W2970990801","https://openalex.org/W2981030070","https://openalex.org/W3003266338","https://openalex.org/W3016361525","https://openalex.org/W3099815795","https://openalex.org/W3126478517","https://openalex.org/W3165566076","https://openalex.org/W4288348579","https://openalex.org/W4293864724","https://openalex.org/W6638667902","https://openalex.org/W6695676441","https://openalex.org/W6712173889","https://openalex.org/W6719911377","https://openalex.org/W6737327832","https://openalex.org/W6739378191","https://openalex.org/W6740881549","https://openalex.org/W6741857108","https://openalex.org/W6748579715","https://openalex.org/W6753243525","https://openalex.org/W6756168450","https://openalex.org/W6758978475","https://openalex.org/W6780226713","https://openalex.org/W6789967057","https://openalex.org/W6841393079"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W2912415823","https://openalex.org/W2110944602","https://openalex.org/W3213722473"],"abstract_inverted_index":{"Deep":[0,120],"Q":[1,73,121,164],"learning":[2,122],"(DQN)":[3],"has":[4],"enabled":[5],"robot":[6,127],"agents":[7],"to":[8,70,94,206],"accomplish":[9],"vision":[10,41,125],"based":[11,126],"tasks":[12,65],"that":[13,30,60,157,202],"seemed":[14],"out":[15],"of":[16,27,34,56,63,115,191],"reach.":[17],"Despite":[18],"recent":[19],"success":[20,101,177],"stories,":[21],"there":[22],"are":[23,172,180,193],"still":[24],"several":[25],"sources":[26],"computational":[28],"complexity":[29],"challenge":[31],"the":[32,38,45,71,88,113,133,140,162],"performance":[33],"DQN.":[35,188],"We":[36,58,155],"place":[37],"focus":[39],"on":[40,52],"manipulation":[42,128],"tasks,":[43,198],"where":[44,199],"correct":[46],"action":[47],"selection":[48],"is":[49,204,222],"often":[50],"predicated":[51],"a":[53,99],"small":[54],"number":[55],"pixels.":[57],"observe":[59],"in":[61,104,124,166,196],"some":[62],"these":[64],"DQN":[66,92,160],"does":[67],"not":[68,79],"converge":[69],"optimal":[72,82,163],"function,":[74],"and":[75,83,97,149,179],"their":[76,143],"values":[77,165],"do":[78],"separate":[80],"well":[81],"suboptimal":[84],"actions.":[85],"In":[86,108],"consequence,":[87],"policies":[89,171,209],"obtained":[90],"with":[91,182,187,210,224],"tend":[93],"be":[95],"brittle":[96],"manifest":[98,175],"low":[100],"rate,":[102,178],"especially":[103],"long":[105],"horizon":[106],"tasks.":[107,129],"this":[109,221],"work":[110],"we":[111,200],"show":[112,156,201],"benefits":[114,190],"Reward":[116,130],"Machines":[117],"(RMs)":[118],"for":[119],"(DQRM)":[123],"machines":[131],"decompose":[132],"task":[134,147],"at":[135],"an":[136],"abstract":[137,168],"level,":[138],"inform":[139],"agent":[141],"about":[142],"current":[144],"stage":[145],"along":[146],"completion,":[148],"guide":[150],"them":[151],"via":[152],"dense":[153,225],"rewards.":[154],"RMs":[158,192],"help":[159],"learn":[161,207],"each":[167],"state.":[169],"Their":[170],"more":[173,194],"robust,":[174],"higher":[176],"learned":[181],"fewer":[183,214],"training":[184,215],"steps":[185,216],"compared":[186],"The":[189],"evident":[195],"long-horizon":[197],"DQRM":[203],"able":[205],"good-quality":[208],"six":[211],"times":[212,213],"than":[217],"DQN,":[218],"even":[219],"when":[220],"equipped":[223],"reward":[226],"shaping.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}