{"id":"https://openalex.org/W4383066631","doi":"https://doi.org/10.1109/icra48891.2023.10161081","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","display_name":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383066631","doi":"https://doi.org/10.1109/icra48891.2023.10161081"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5100330660","display_name":"Yi Liu","orcid":"https://orcid.org/0009-0001-4797-7826"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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":"Yi Liu","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035819520","display_name":"Gaurav Datta","orcid":"https://orcid.org/0000-0002-2872-5420"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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":"Gaurav Datta","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010917268","display_name":"Ellen Novoseller","orcid":null},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ellen Novoseller","raw_affiliation_strings":["Army Research Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Research Lab","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103065575","display_name":"Daniel S. Brown","orcid":"https://orcid.org/0000-0002-9570-1832"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel S. Brown","raw_affiliation_strings":["University of Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4474,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.9104939,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2921","last_page":"2928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987999796867371,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8446252346038818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8185643553733826},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7164139151573181},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.643890380859375},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.6267365217208862},{"id":"https://openalex.org/keywords/preference-elicitation","display_name":"Preference elicitation","score":0.6002373099327087},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5825643539428711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5643060207366943},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5642755031585693},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.55162113904953},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5317726731300354},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5007803440093994},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.4667523205280304},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4340746998786926}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8446252346038818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185643553733826},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7164139151573181},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.643890380859375},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.6267365217208862},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.6002373099327087},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5825643539428711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5643060207366943},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5642755031585693},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.55162113904953},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5317726731300354},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5007803440093994},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.4667523205280304},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4340746998786926},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/15","score":0.4300000071525574,"display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":103,"referenced_works":["https://openalex.org/W1502364872","https://openalex.org/W1577352482","https://openalex.org/W1837766154","https://openalex.org/W1898511152","https://openalex.org/W1986014385","https://openalex.org/W1997543377","https://openalex.org/W2077673559","https://openalex.org/W2089954205","https://openalex.org/W2116671302","https://openalex.org/W2123459560","https://openalex.org/W2290104316","https://openalex.org/W2528489519","https://openalex.org/W2560678327","https://openalex.org/W2573393487","https://openalex.org/W2604382266","https://openalex.org/W2735318784","https://openalex.org/W2740210681","https://openalex.org/W2741086304","https://openalex.org/W2770616710","https://openalex.org/W2781726626","https://openalex.org/W2783091972","https://openalex.org/W2804020409","https://openalex.org/W2889347284","https://openalex.org/W2902125520","https://openalex.org/W2920362155","https://openalex.org/W2937555108","https://openalex.org/W2949361666","https://openalex.org/W2958484796","https://openalex.org/W2962787969","https://openalex.org/W2962937519","https://openalex.org/W2963355572","https://openalex.org/W2964067469","https://openalex.org/W2964327849","https://openalex.org/W2965175271","https://openalex.org/W2981547136","https://openalex.org/W2994446013","https://openalex.org/W2999054007","https://openalex.org/W3006334608","https://openalex.org/W3008082783","https://openalex.org/W3028766998","https://openalex.org/W3029829149","https://openalex.org/W3031634197","https://openalex.org/W3035644784","https://openalex.org/W3039563104","https://openalex.org/W3091243689","https://openalex.org/W3093784762","https://openalex.org/W3171469166","https://openalex.org/W3187722890","https://openalex.org/W3199458926","https://openalex.org/W3202512200","https://openalex.org/W3210326730","https://openalex.org/W4243917683","https://openalex.org/W4283784806","https://openalex.org/W4287122174","https://openalex.org/W4288088514","https://openalex.org/W4288093757","https://openalex.org/W4288284400","https://openalex.org/W4289288058","https://openalex.org/W4289294484","https://openalex.org/W4298206671","https://openalex.org/W4313598235","https://openalex.org/W4321392130","https://openalex.org/W4382239602","https://openalex.org/W6677285668","https://openalex.org/W6678474417","https://openalex.org/W6696380822","https://openalex.org/W6730700719","https://openalex.org/W6739585900","https://openalex.org/W6741832191","https://openalex.org/W6747473740","https://openalex.org/W6748210908","https://openalex.org/W6748392304","https://openalex.org/W6751494529","https://openalex.org/W6751526458","https://openalex.org/W6753960536","https://openalex.org/W6754162236","https://openalex.org/W6755864697","https://openalex.org/W6756256016","https://openalex.org/W6756303580","https://openalex.org/W6756908582","https://openalex.org/W6760405395","https://openalex.org/W6761392374","https://openalex.org/W6761908843","https://openalex.org/W6765813175","https://openalex.org/W6766451708","https://openalex.org/W6767081328","https://openalex.org/W6768397756","https://openalex.org/W6769043678","https://openalex.org/W6769174716","https://openalex.org/W6769397037","https://openalex.org/W6769570503","https://openalex.org/W6771598146","https://openalex.org/W6773844738","https://openalex.org/W6777656069","https://openalex.org/W6778229956","https://openalex.org/W6785034342","https://openalex.org/W6796168157","https://openalex.org/W6797052142","https://openalex.org/W6799150178","https://openalex.org/W6800887884","https://openalex.org/W6802215095","https://openalex.org/W6803213246","https://openalex.org/W6848774067"],"related_works":["https://openalex.org/W1562775108","https://openalex.org/W2126528747","https://openalex.org/W3210700034","https://openalex.org/W1488237461","https://openalex.org/W4286900255","https://openalex.org/W2914800632","https://openalex.org/W2962903234","https://openalex.org/W4200207182","https://openalex.org/W2157910771","https://openalex.org/W4386241784"],"abstract_inverted_index":{"Preference-based":[0],"reinforcement":[1],"learning":[2,161],"(PbRL)":[3],"can":[4,102,123],"enable":[5,139],"robots":[6,140],"to":[7,9,29,141],"learn":[8,142],"perform":[10],"tasks":[11],"based":[12,119,145],"on":[13,120,146],"an":[14],"individual's":[15],"preferences":[16,148],"without":[17,126],"requiring":[18],"a":[19,30,38,60,73,109],"hand-crafted":[20],"re-ward":[21],"function.":[22],"However,":[23],"existing":[24],"approaches":[25],"either":[26],"assume":[27],"access":[28],"high-fidelity":[31],"simulator":[32],"or":[33,36],"analytic":[34],"model":[35,63,76],"take":[37],"model-free":[39,96],"approach":[40],"that":[41,72,135,151],"requires":[42],"extensive,":[43],"possibly":[44],"unsafe":[45],"online":[46],"environment":[47,93],"interactions.":[48],"In":[49,67],"this":[50],"paper,":[51],"we":[52,69],"study":[53],"the":[54,78],"benefits":[55,80],"and":[56,87,106,115,154,165],"challenges":[57],"of":[58,111],"using":[59],"learned":[61,74,136],"dynamics":[62,75,137],"when":[64,81],"performing":[65,82],"PbRL.":[66],"particular,":[68],"provide":[70],"evidence":[71],"offers":[77],"following":[79],"PbRL:":[83],"(1)":[84],"preference":[85,100,160],"elicitation":[86],"policy":[88],"optimization":[89],"require":[90],"significantly":[91],"fewer":[92],"interactions":[94],"than":[95,158],"PbRL,":[97],"(2)":[98],"diverse":[99],"queries":[101],"be":[103,124],"synthesized":[104],"safely":[105],"efficiently":[107],"as":[108],"byproduct":[110],"standard":[112],"model-based":[113],"RL,":[114],"(3)":[116],"reward":[117],"pre-training":[118],"suboptimal":[121],"demonstrations":[122],"performed":[125],"any":[127],"environmental":[128],"interaction.":[129],"Our":[130],"paper":[131],"provides":[132],"empirical":[133],"ev-idence":[134],"models":[138],"customized":[143],"policies":[144],"user":[147],"in":[149],"ways":[150],"are":[152,167],"safer":[153],"more":[155],"sample":[156],"efficient":[157],"prior":[159],"approaches.":[162],"Supplementary":[163],"materials":[164],"code":[166],"available":[168],"at":[169],"https://sites.google.com/berkeley.edu/mop-rl.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}