{"id":"https://openalex.org/W3205261317","doi":"https://doi.org/10.1109/icra48506.2021.9560733","title":"Representation Matters: Improving Perception and Exploration for Robotics","display_name":"Representation Matters: Improving Perception and Exploration for Robotics","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3205261317","doi":"https://doi.org/10.1109/icra48506.2021.9560733","mag":"3205261317"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.01758","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002747297","display_name":"Markus Wulfmeier","orcid":"https://orcid.org/0000-0003-1802-4492"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Markus Wulfmeier","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037305533","display_name":"Arunkumar Byravan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arunkumar Byravan","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026388725","display_name":"Tim Hertweck","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tim Hertweck","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018830387","display_name":"Irina Higgins","orcid":"https://orcid.org/0000-0002-1890-2091"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Irina Higgins","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110700198","display_name":"Ankush Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ankush Gupta","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091197128","display_name":"Tejas Kulkarni","orcid":"https://orcid.org/0009-0005-1627-0878"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tejas Kulkarni","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103531364","display_name":"Malcolm Reynolds","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Malcolm Reynolds","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083439126","display_name":"Denis Teplyashin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Denis Teplyashin","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018196238","display_name":"Roland Hafner","orcid":"https://orcid.org/0000-0001-8061-8828"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Roland Hafner","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054636066","display_name":"Thomas Lampe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Lampe","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041323275","display_name":"Martin Riedmiller","orcid":"https://orcid.org/0000-0002-8465-5690"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"funder","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin Riedmiller","raw_affiliation_strings":["DeepMind, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.589,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.838294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":80,"max":82},"biblio":{"volume":null,"issue":null,"first_page":"6512","last_page":"6519"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9999,"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":0.9999,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9963,"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":0.9959,"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/observability","display_name":"Observability","score":0.8499071},{"id":"https://openalex.org/keywords/representation","display_name":"Representation","score":0.75575125}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.8499071},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.76316035},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.75575125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.72598207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6521008},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5993869},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.58832216},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5506154},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4889561},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47227916},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.42443785},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32762045},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.32760802},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11402595},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0866459},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2011.01758","pdf_url":"https://arxiv.org/pdf/2011.01758","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2011.01758","pdf_url":"https://arxiv.org/pdf/2011.01758","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":87,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1554318634","https://openalex.org/W1594201624","https://openalex.org/W1757796397","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W1968962398","https://openalex.org/W2089497633","https://openalex.org/W2100495367","https://openalex.org/W2116386744","https://openalex.org/W2158782408","https://openalex.org/W2296073425","https://openalex.org/W2343938449","https://openalex.org/W2553701371","https://openalex.org/W2556477470","https://openalex.org/W2567015638","https://openalex.org/W2604626881","https://openalex.org/W2726187156","https://openalex.org/W2734325473","https://openalex.org/W2735995851","https://openalex.org/W2737215407","https://openalex.org/W2744921630","https://openalex.org/W2753738274","https://openalex.org/W2781585732","https://openalex.org/W2788781499","https://openalex.org/W2803281228","https://openalex.org/W2810132790","https://openalex.org/W2810785043","https://openalex.org/W2823112946","https://openalex.org/W2842511635","https://openalex.org/W2902286283","https://openalex.org/W2902476877","https://openalex.org/W2903538854","https://openalex.org/W2908460759","https://openalex.org/W2911448865","https://openalex.org/W2913954345","https://openalex.org/W2920362155","https://openalex.org/W2950614095","https://openalex.org/W2950662112","https://openalex.org/W2952578114","https://openalex.org/W2953469440","https://openalex.org/W2954142106","https://openalex.org/W2954970763","https://openalex.org/W2955368974","https://openalex.org/W2962715211","https://openalex.org/W2962864381","https://openalex.org/W2963147844","https://openalex.org/W2963177395","https://openalex.org/W2963199420","https://openalex.org/W2963311874","https://openalex.org/W2963438456","https://openalex.org/W2963523627","https://openalex.org/W2963611966","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2964118020","https://openalex.org/W2964327384","https://openalex.org/W2964342357","https://openalex.org/W2970241862","https://openalex.org/W2971202257","https://openalex.org/W2981344907","https://openalex.org/W2991156573","https://openalex.org/W2995298643","https://openalex.org/W3005680577","https://openalex.org/W3024554557","https://openalex.org/W3030142708","https://openalex.org/W3032377877","https://openalex.org/W3035060554","https://openalex.org/W3041890730","https://openalex.org/W3046190872","https://openalex.org/W3091471537","https://openalex.org/W3101283005","https://openalex.org/W3115293622","https://openalex.org/W3173031723","https://openalex.org/W4214717370","https://openalex.org/W4288018521","https://openalex.org/W4288094104","https://openalex.org/W4288289109","https://openalex.org/W4288294128","https://openalex.org/W4295246696","https://openalex.org/W4297744728","https://openalex.org/W4297795161","https://openalex.org/W4297808394","https://openalex.org/W4298018319","https://openalex.org/W4298857966","https://openalex.org/W4300198501","https://openalex.org/W4300799055"],"related_works":["https://openalex.org/W4312300846","https://openalex.org/W4206221578","https://openalex.org/W3157641275","https://openalex.org/W3029572990","https://openalex.org/W2967463586","https://openalex.org/W2765830098","https://openalex.org/W2615757685","https://openalex.org/W2517338020","https://openalex.org/W2046459260","https://openalex.org/W1971989957"],"abstract_inverted_index":{"Projecting":[0],"high-dimensional":[1],"environment":[2],"observations":[3],"into":[4],"lower-dimensional":[5],"structured":[6],"representations":[7,73,89,136],"can":[8,125,137],"considerably":[9],"improve":[10,127],"data-efficiency":[11],"for":[12,159,165,191,211,222],"reinforcement":[13],"learning":[14],"in":[15,74,92,115,129,213],"domains":[16],"with":[17],"limited":[18,189],"data":[19],"such":[20,54],"as":[21,95,101,143,197],"robotics.":[22],"Can":[23],"a":[24,55,66,102,198,201,208],"single":[25],"generally":[26],"useful":[27],"representation":[28,44,57,112,176,210],"be":[29,46],"found?":[30],"In":[31,60],"order":[32],"to":[33,40,97,140,182,217],"answer":[34],"this":[35,61],"question,":[36],"it":[37],"is":[38,113,163],"important":[39],"understand":[41],"how":[42],"the":[43,49,75,98,108,174],"will":[45],"used":[47],"by":[48,152],"agent":[50,144],"and":[51,71,83,122,132,178],"what":[52,206],"properties":[53],"good":[56,209],"should":[58],"have.":[59],"paper":[62],"we":[63],"systematically":[64],"evaluate":[65],"number":[67],"of":[68,77,85,104,110,117,169,205],"common":[69,150],"learnt":[70],"hand-engineered":[72,227],"context":[76],"three":[78,118],"robotics":[79],"tasks:":[80],"lifting,":[81],"stacking":[82],"pushing":[84],"3D":[86],"blocks.":[87],"The":[88],"are":[90],"evaluated":[91,114],"two":[93],"use-cases:":[94],"input":[96,175,192],"agent,":[99],"or":[100,226],"source":[103],"auxiliary":[105,184],"tasks.":[106],"Furthermore,":[107],"value":[109],"each":[111],"terms":[116],"properties:":[119],"dimensionality,":[120],"observability":[121,168],"disentanglement.":[123],"We":[124],"significantly":[126],"performance":[128],"both":[130],"use-cases":[131],"demonstrate":[133],"that":[134],"some":[135],"perform":[138],"commensurate":[139],"simulator":[141],"states":[142],"inputs.":[145],"Finally,":[146],"our":[147],"results":[148],"challenge":[149],"intuitions":[151],"demonstrating":[153],"that:":[154],"1)":[155],"dimensionality":[156],"strongly":[157],"matters":[158],"task":[160],"generation,":[161],"but":[162,186],"negligible":[164],"inputs,":[166],"2)":[167],"task-relevant":[170],"aspects":[171],"mostly":[172],"affects":[173],"use-case,":[177],"3)":[179],"disentanglement":[180],"leads":[181],"better":[183],"tasks,":[185],"has":[187],"only":[188],"benefits":[190],"representations.":[193,228],"This":[194],"work":[195],"serves":[196],"step":[199],"towards":[200],"more":[202,219],"systematic":[203],"understanding":[204],"makes":[207],"control":[212],"robotics,":[214],"enabling":[215],"practitioners":[216],"make":[218],"informed":[220],"choices":[221],"developing":[223],"new":[224],"learned":[225]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3205261317","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-04-17T03:05:20.194985","created_date":"2021-10-25"}