{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T22:15:16Z","timestamp":1770329716961,"version":"3.49.0"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/lra.2023.3271520","type":"journal-article","created":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T01:22:41Z","timestamp":1683768161000},"page":"3780-3787","source":"Crossref","is-referenced-by-count":15,"title":["Off-Policy Evaluation With Online Adaptation for Robot Exploration in Challenging Environments"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8142-1629","authenticated-orcid":false,"given":"Yafei","family":"Hu","sequence":"first","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6494-6810","authenticated-orcid":false,"given":"Junyi","family":"Geng","sequence":"additional","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4630-0805","authenticated-orcid":false,"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Keller","sequence":"additional","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8373-4688","authenticated-orcid":false,"given":"Sebastian","family":"Scherer","sequence":"additional","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"levine","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref12","article-title":"Benchmarks for deep off-policy evaluation","author":"fu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","author":"stadie","year":"2015"},{"key":"ref14","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","author":"kumar","year":"0","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.55417\/fr.2022023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.004"},{"key":"ref11","first-page":"485","article-title":"Doubly robust policy evaluation and optimization","volume":"29","author":"dudik","year":"2015","journal-title":"Stat Sci"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3133591"},{"key":"ref32","first-page":"2318","article-title":"DualDICE: Behavior-agnostic estimation of discounted stationary distribution corrections","author":"nachum","year":"0","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref2","first-page":"146","article-title":"A frontier-based approach for autonomous exploration brian yamauchi","author":"yamauchi","year":"0","journal-title":"Proc IEEE Int Symp Comput Intell Robot Automat"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IRDS.2002.1041446"},{"key":"ref17","first-page":"1816","article-title":"Information-theoretic exploration with Bayesian optimization","author":"shi","year":"0","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref16","author":"thrun","year":"2005","journal-title":"Probabilistic Robotics"},{"key":"ref19","article-title":"Episodic curiosity through reachability","author":"savinov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068923"},{"key":"ref24","first-page":"2139","article-title":"Data-efficient off-policy policy evaluation for reinforcement learning","author":"thomas","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref23","article-title":"Empirical study of off-policy policy evaluation for reinforcement learning","author":"voloshin","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref20","first-page":"2721","article-title":"Count-based exploration with neural density models","author":"ostrovski","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref22","article-title":"Curious exploration via structured world models yields zero-shot object manipulation","author":"sancaktar","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref21","first-page":"1","article-title":"# exploration: A study of count-based exploration for deep reinforcement learning","author":"tang","year":"0","journal-title":"Proc 31st Conf Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref27","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref29","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"Proc 35th Int Conf Mach"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463213"},{"key":"ref7","article-title":"Learning exploration policies for navigation","author":"chen","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341657"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref3","first-page":"1479","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"0","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145971"},{"key":"ref5","article-title":"Ride: Rewarding impact-driven exploration for procedurally-generated environments","author":"raileanu","year":"0","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10102643\/10111084.pdf?arnumber=10111084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T18:41:00Z","timestamp":1723056060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10111084\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":33,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3271520","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}