{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T22:53:12Z","timestamp":1774911192621,"version":"3.50.1"},"reference-count":20,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["JP23KJ1585"],"award-info":[{"award-number":["JP23KJ1585"]}]},{"name":"JSPS KAKENHI","award":["JP24K03018"],"award-info":[{"award-number":["JP24K03018"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Automat. Mag."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/mra.2026.3650847","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:54:07Z","timestamp":1768856047000},"page":"151-166","source":"Crossref","is-referenced-by-count":2,"title":["DAPPER: Discriminability-Aware Policy-to-Policy Preference-Based Reinforcement Learning for Query-Efficient Robot Skill Acquisition"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3358-9520","authenticated-orcid":false,"given":"Yuki","family":"Kadokawa","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology, Nara, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7401-2173","authenticated-orcid":false,"given":"Jonas","family":"Frey","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8556-2819","authenticated-orcid":false,"given":"Takahiro","family":"Miki","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3545-4814","authenticated-orcid":false,"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology, Nara, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-4990","authenticated-orcid":false,"given":"Marco","family":"Hutter","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Rudin","year":"2022"},{"key":"ref2","first-page":"342","article-title":"Learning agile skills via adversarial imitation of rough partial demonstrations","volume-title":"Proc. Conf. Robot Learn.","author":"Li","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1774"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2024.3403833"},{"key":"ref6","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Christiano","year":"2017"},{"key":"ref7","article-title":"SURF: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Park","year":"2022"},{"key":"ref8","first-page":"8229","article-title":"RIME: Robust preference-based reinforcement learning with noisy preferences","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cheng","year":"2024"},{"key":"ref9","article-title":"Query-policy misalignment in preference-based reinforcement learning","author":"Hu","year":"2024"},{"key":"ref10","article-title":"Open problems and fundamental limitations of reinforcement learning from human feedback","volume-title":"Proc. Trans. Mach. Learn. Res.","author":"Casper","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.584075"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.04.009"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104366"},{"key":"ref14","first-page":"1177","article-title":"Asking easy questions: A user-friendly approach to active reward learning","volume-title":"Proc. Conf. Robot Learn.","author":"Byk","year":"2020"},{"key":"ref15","first-page":"6152","article-title":"PEBBLE: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Lee","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref17","article-title":"Rewards encoding environment dynamics improves preference-based reinforcement learning","author":"Metcalf","year":"2022"},{"key":"ref18","article-title":"Preference-based reinforcement learning: A preliminary survey","volume-title":"Proc. ECML\/PKDD-13 Workshop","author":"Wirth","year":"2013"},{"key":"ref19","article-title":"Vision-language models are zero-shot reward models for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rocamonde","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01370"}],"container-title":["IEEE Robotics & Automation Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/100\/11456130\/11358816.pdf?arnumber=11358816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:49:02Z","timestamp":1774554542000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11358816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":20,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/mra.2026.3650847","relation":{},"ISSN":["1070-9932","1558-223X"],"issn-type":[{"value":"1070-9932","type":"print"},{"value":"1558-223X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}