{"id":"https://openalex.org/W7124898582","doi":"https://doi.org/10.1109/mra.2026.3650847","title":"DAPPER: Discriminability-Aware Policy-to-Policy Preference-Based Reinforcement Learning for Query-Efficient Robot Skill Acquisition","display_name":"DAPPER: Discriminability-Aware Policy-to-Policy Preference-Based Reinforcement Learning for Query-Efficient Robot Skill Acquisition","publication_year":2026,"publication_date":"2026-01-19","ids":{"openalex":"https://openalex.org/W7124898582","doi":"https://doi.org/10.1109/mra.2026.3650847"},"language":null,"primary_location":{"id":"doi:10.1109/mra.2026.3650847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mra.2026.3650847","pdf_url":null,"source":{"id":"https://openalex.org/S132261465","display_name":"IEEE Robotics & Automation Magazine","issn_l":"1070-9932","issn":["1070-9932","1558-223X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics & Automation Magazine","raw_type":"journal-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/A5001325713","display_name":"Yuki Kadokawa","orcid":"https://orcid.org/0000-0003-3358-9520"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Kadokawa","raw_affiliation_strings":["Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3358-9520","affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016683949","display_name":"Jonas Frey","orcid":"https://orcid.org/0000-0002-7401-2173"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jonas Frey","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7401-2173","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016407319","display_name":"Takahiro Miki","orcid":"https://orcid.org/0000-0001-8556-2819"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Takahiro Miki","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-8556-2819","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042074952","display_name":"Takamitsu Matsubara","orcid":"https://orcid.org/0000-0003-3545-4814"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takamitsu Matsubara","raw_affiliation_strings":["Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3545-4814","affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063709131","display_name":"M. HUTTER","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marco Hutter","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-4285-4990","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.1051,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96113395,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"33","issue":"1","first_page":"151","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3393000066280365,"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":0.3393000066280365,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.09920000284910202,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11106","display_name":"Data Management and Algorithms","score":0.09130000323057175,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.6834999918937683},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.6410999894142151},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5680999755859375},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5497000217437744},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5188000202178955},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5102999806404114},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.4893999993801117},{"id":"https://openalex.org/keywords/preference-elicitation","display_name":"Preference elicitation","score":0.4189000129699707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777899980545044},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6834999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6438000202178955},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.6410999894142151},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5680999755859375},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5497000217437744},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5435000061988831},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.4893999993801117},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.4189000129699707},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mra.2026.3650847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mra.2026.3650847","pdf_url":null,"source":{"id":"https://openalex.org/S132261465","display_name":"IEEE Robotics & Automation Magazine","issn_l":"1070-9932","issn":["1070-9932","1558-223X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics & Automation Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7738322615623474}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Preference-based":[0],"reinforcement":[1],"learning":[2,6,53],"(PBRL)":[3],"enables":[4],"policy":[5,39,94,113],"through":[7],"simple":[8],"queries":[9,21,50,98],"comparing":[10,100],"trajectories":[11,101],"from":[12,34,102,108,138],"a":[13,64,77,92,146],"single":[14,93],"policy.":[15],"While":[16],"human":[17,30,65],"responses":[18],"to":[19,25,72,150],"these":[20],"make":[22],"it":[23,164],"possible":[24],"learn":[26],"policies":[27,137],"aligned":[28],"with":[29,127],"preferences,":[31],"PBRL":[32],"suffers":[33],"low":[35],"query":[36,82,199],"efficiency,":[37,200],"as":[38,76,105],"bias":[40],"limits":[41],"trajectory":[42,69,128],"diversity":[43,111],"and":[44,95,144,170,180,187],"reduces":[45],"the":[46,155,167,175],"number":[47],"of":[48,158,177],"discriminable":[49,160],"available":[51],"for":[52,80],"preferences.":[54],"This":[55],"article":[56],"identifies":[57],"preference":[58,125,152,168,171,204],"discriminability,":[59,153],"which":[60,68,123],"quantifies":[61],"how":[62],"easily":[63,181],"can":[66],"judge":[67],"is":[70],"closer":[71],"their":[73],"ideal":[74],"behavior,":[75],"key":[78],"metric":[79],"improving":[81],"efficiency.":[83],"To":[84],"address":[85],"this,":[86],"we":[87],"move":[88],"beyond":[89],"comparisons":[90],"within":[91],"instead":[96],"generate":[97],"by":[99,131],"multiple":[103,132],"policies,":[104],"training":[106],"them":[107],"scratch":[109,139],"promotes":[110],"without":[112],"bias.":[114],"We":[115],"propose":[116],"discriminability-aware":[117],"policy-to-policy":[118],"preference-based":[119],"efficient":[120],"RL":[121],"(DAPPER),":[122],"integrates":[124],"discriminability":[126,172,205],"diversification":[129],"achieved":[130],"policies.":[133,183],"DAPPER":[134,194],"trains":[135],"new":[136],"after":[140],"each":[141],"reward":[142,169],"update":[143],"employs":[145],"discriminator":[147],"that":[148,193],"learns":[149],"estimate":[151],"enabling":[154],"prioritized":[156],"sampling":[157],"more":[159],"queries.":[161],"During":[162],"training,":[163],"jointly":[165],"maximizes":[166],"score,":[173],"encouraging":[174],"discovery":[176],"highly":[178],"rewarding":[179],"distinguishable":[182],"Experiments":[184],"in":[185,198],"simulated":[186],"real-world":[188],"legged":[189],"robot":[190],"environments":[191],"demonstrate":[192],"outperforms":[195],"previous":[196],"methods":[197],"particularly":[201],"under":[202],"challenging":[203],"conditions.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-26T06:05:38.182114","created_date":"2026-01-21T00:00:00"}