{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T16:42:51Z","timestamp":1776876171208,"version":"3.51.2"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JST AIP Acceleration Research","award":["JPMJCR20U3"],"award-info":[{"award-number":["JPMJCR20U3"]}]},{"name":"Moonshot R&D","award":["JPMJPS2011"],"award-info":[{"award-number":["JPMJPS2011"]}]},{"name":"CREST","award":["JPMJCR2015"],"award-info":[{"award-number":["JPMJCR2015"]}]},{"name":"JSPS KAKENHI","award":["JP19H01115"],"award-info":[{"award-number":["JP19H01115"]}]},{"name":"JSPS KAKENHI","award":["JP19K20370"],"award-info":[{"award-number":["JP19K20370"]}]},{"DOI":"10.13039\/501100004721","name":"University of Tokyo","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004721","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017657","name":"Komatsu","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017657","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/lra.2023.3296933","type":"journal-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T21:08:07Z","timestamp":1689800887000},"page":"5536-5543","source":"Crossref","is-referenced-by-count":7,"title":["Learning Adaptive Policies for Autonomous Excavation Under Various Soil Conditions by Adversarial Domain Sampling"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6895-9088","authenticated-orcid":false,"given":"Takayuki","family":"Osa","sequence":"first","affiliation":[{"name":"University of Tokyo, Tokyo, Japan"}]},{"given":"Naoto","family":"Osajima","sequence":"additional","affiliation":[{"name":"Kyushu Institute of Technology, Fukuoka, Japan"}]},{"given":"Masanori","family":"Aizawa","sequence":"additional","affiliation":[{"name":"Komatsu Ltd., Kanagawa, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3712-3691","authenticated-orcid":false,"given":"Tatsuya","family":"Harada","sequence":"additional","affiliation":[{"name":"University of Tokyo, Tokyo, Japan"}]}],"member":"263","reference":[{"key":"ref13","first-page":"403","article-title":"Legged locomotion in challenging terrains using egocentric vision","author":"agarwal","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref15","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.075"},{"key":"ref11","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"rakelly","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008914201877"},{"key":"ref1","first-page":"957","article-title":"Experimental robotic excavation with fuzzy logic and neural networks","author":"shi","year":"0","journal-title":"Proc IEEE Int Conf Robot Automat"},{"key":"ref17","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3058071"},{"key":"ref18","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref23","first-page":"16020","article-title":"Adversarial attack generation empowered by min-max optimization","author":"wang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","article-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","author":"sukhbaatar","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3097264"},{"key":"ref22","first-page":"8921","article-title":"Adversarial example games","author":"bose","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref28","first-page":"2021","article-title":"Implicit under-parameterization inhibits data-efficient deep reinforcement learning","author":"kumar","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref8","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3189834"},{"key":"ref9","first-page":"557","article-title":"Scaling up multi-task robotic reinforcement learning","author":"kalashnikov","year":"0","journal-title":"Proc 5th Conf Robot Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2017.1297735"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40686-7_25"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.10.301"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3140781"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10185095\/10187614.pdf?arnumber=10187614","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T18:00:50Z","timestamp":1692036050000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10187614\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":28,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3296933","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}