{"id":"https://openalex.org/W4225737910","doi":"https://doi.org/10.1177/02783649221078031","title":"Inducing structure in reward learning by learning features","display_name":"Inducing structure in reward learning by learning features","publication_year":2022,"publication_date":"2022-04-01","ids":{"openalex":"https://openalex.org/W4225737910","doi":"https://doi.org/10.1177/02783649221078031"},"language":"en","primary_location":{"id":"doi:10.1177/02783649221078031","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649221078031","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1177/02783649221078031","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034978137","display_name":"Andreea Bobu","orcid":"https://orcid.org/0000-0002-9507-7427"},"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":true,"raw_author_name":"Andreea Bobu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9507-7427","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083812172","display_name":"Marius Wiggert","orcid":null},"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":"Marius Wiggert","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045155646","display_name":"Claire J. Tomlin","orcid":"https://orcid.org/0000-0003-3192-3185"},"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":"Claire Tomlin","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005997281","display_name":"Anca D. Dragan","orcid":"https://orcid.org/0000-0001-6312-5466"},"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":"Anca D Dragan","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5034978137"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":2.6243,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90980748,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"41","issue":"5","first_page":"497","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9965000152587891,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9570000171661377,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7224858999252319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6878466606140137},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6563608050346375},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5833920240402222},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5581492185592651},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5138304829597473},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4993572235107422},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45497772097587585},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4256684184074402},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.41963914036750793},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4148324131965637},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.18443217873573303},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12439247965812683}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7224858999252319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6878466606140137},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6563608050346375},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5833920240402222},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5581492185592651},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5138304829597473},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4993572235107422},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45497772097587585},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4256684184074402},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.41963914036750793},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4148324131965637},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.18443217873573303},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12439247965812683},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/02783649221078031","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649221078031","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1177/02783649221078031","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649221078031","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G402934692","display_name":null,"funder_award_id":"FA9550-17-1-0308","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G4532442909","display_name":null,"funder_award_id":"FA8750-18-C-0101","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6345352953","display_name":null,"funder_award_id":"20-1-2736","funder_id":"https://openalex.org/F4320338298","funder_display_name":"Office of Naval Research Global"}],"funders":[{"id":"https://openalex.org/F4320320875","display_name":"Deutscher Akademischer Austauschdienst","ror":"https://ror.org/039djdh30"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338298","display_name":"Office of Naval Research Global","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W147348363","https://openalex.org/W1551864151","https://openalex.org/W1773113936","https://openalex.org/W1837766154","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2032558547","https://openalex.org/W2061562262","https://openalex.org/W2156163138","https://openalex.org/W2157289187","https://openalex.org/W2169498096","https://openalex.org/W2310516540","https://openalex.org/W2565370028","https://openalex.org/W2596585349","https://openalex.org/W2604272474","https://openalex.org/W2612690371","https://openalex.org/W2792089292","https://openalex.org/W2962951365","https://openalex.org/W2963507484","https://openalex.org/W2963731007","https://openalex.org/W2990138404","https://openalex.org/W3003858867","https://openalex.org/W3101780148","https://openalex.org/W3106171760","https://openalex.org/W3207966700","https://openalex.org/W4212774754","https://openalex.org/W4230674625","https://openalex.org/W4242073862","https://openalex.org/W4288076204"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W3134526803","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867"],"abstract_inverted_index":{"Reward":[0],"learning":[1,91,150],"enables":[2],"robots":[3],"to":[4,66,76,100,123,138,162],"learn":[5,51,68,98,124,136],"adaptable":[6],"behaviors":[7],"from":[8,54,127,165],"human":[9,87,112,180],"input.":[10],"Traditional":[11],"methods":[12,50],"model":[13],"the":[14,28,55,63,69,92,128,173,184,195],"reward":[15,143,149,197],"as":[16,167,169],"a":[17,31,83,104,108,142,199,209,216,221],"linear":[18],"function":[19],"of":[20,111,172,194],"hand-crafted":[21],"features,":[22],"but":[23,58],"that":[24,71,120],"requires":[25],"specifying":[26],"all":[27,159],"relevant":[29],"features":[30,70,93,116,126,160,174],"priori,":[32],"which":[33],"is":[34,60],"impossible":[35],"for":[36,114],"real-world":[37],"tasks.":[38],"To":[39],"get":[40],"around":[41],"this":[42,59,205],"issue,":[43],"recent":[44],"deep":[45,200],"Inverse":[46],"Reinforcement":[47],"Learning":[48],"(IRL)":[49],"rewards":[52],"directly":[53],"raw":[56,129],"state":[57,130],"challenging":[61],"because":[62],"robot":[64,133,212],"has":[65],"implicitly":[67],"are":[72,175],"important":[73],"and":[74,95,117,191,214],"how":[75,99,137],"combine":[77,101,139],"them,":[78],"simultaneously.":[79],"Instead,":[80],"we":[81],"propose":[82],"divide-and-conquer":[84],"approach:":[85],"focus":[86],"input":[88,113,181],"specifically":[89,182],"on":[90,183],"separately,":[94],"only":[96],"then":[97,135],"them":[102,140],"into":[103,141],"reward.":[105],"We":[106,152,203],"introduce":[107],"novel":[109],"type":[110],"teaching":[115],"an":[118],"algorithm":[119],"utilizes":[121],"it":[122],"complex":[125],"space.":[131],"The":[132],"can":[134],"using":[144],"demonstrations,":[145],"corrections,":[146],"or":[147],"other":[148],"frameworks.":[151],"demonstrate":[153],"our":[154,186],"method":[155,187],"in":[156,206,215,220],"settings":[157],"where":[158,170],"have":[161],"be":[163],"learned":[164,196],"scratch,":[166],"well":[168],"some":[171],"known.":[176],"By":[177],"first":[178],"focusing":[179],"feature(s),":[185],"decreases":[188],"sample":[189],"complexity":[190],"improves":[192],"generalization":[193],"over":[198],"IRL":[201],"baseline.":[202],"show":[204],"experiments":[207],"with":[208],"physical":[210],"7-DoF":[211],"manipulator,":[213],"user":[217],"study":[218],"conducted":[219],"simulated":[222],"environment.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}