{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:26:26Z","timestamp":1773087986771,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100007780","name":"Kyushu Institute of Technology and Komatsu Company Ltd","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"JSPS KAKENHI","doi-asserted-by":"publisher","award":["JP19K20370"],"award-info":[{"award-number":["JP19K20370"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3140781","type":"journal-article","created":{"date-parts":[[2022,1,6]],"date-time":"2022-01-06T20:29:57Z","timestamp":1641500997000},"page":"4523-4535","source":"Crossref","is-referenced-by-count":20,"title":["Deep Reinforcement Learning With Adversarial Training for Automated Excavation Using Depth Images"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6895-9088","authenticated-orcid":false,"given":"Takayuki","family":"Osa","sequence":"first","affiliation":[{"name":"Department of Human Intelligence Systems, Kyushu Institute of Technology, Fukuoka, Japan"}]},{"given":"Masanori","family":"Aizawa","sequence":"additional","affiliation":[{"name":"Komatsu Ltd., Kanagawa, Japan"}]}],"member":"263","reference":[{"key":"ref39","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1694-0_15"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11009-006-9753-0"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref30","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume":"70","author":"pinto","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref37","first-page":"1","article-title":"Issues in using function approximation for reinforcement learning","author":"thrun","year":"1993","journal-title":"Proc Connectionist Models Summer School"},{"key":"ref36","first-page":"2613","article-title":"Double Q-learning","author":"van hasselt","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref34","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume":"32","author":"silver","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref27","first-page":"1","article-title":"Adversarial attacks on neural network policies","author":"huang","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref29","first-page":"8127","article-title":"Robust reinforcement learning via adversarial training with Langevin dynamics","volume":"33","author":"kamalaruban","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1163\/156855399X00162"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"957","DOI":"10.1109\/ROBOT.1996.503896","article-title":"Experimental robotic excavation with fuzzy logic and neural networks","volume":"1","author":"shi","year":"1996","journal-title":"Proc IEEE Int Conf Robot Autom"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.10.301"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40686-7_25"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385566"},{"key":"ref24","first-page":"1","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref23","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume":"87","author":"kalashnikov","year":"2018","journal-title":"Proc Conf Robot Learn"},{"key":"ref26","first-page":"1","article-title":"Adversarial policies: Attacking deep reinforcement learning","author":"gleave","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref25","first-page":"1","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref10","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref11","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511800474"},{"key":"ref12","first-page":"1","article-title":"Quantile QT-opt for risk-awarevision-based robotic grasping","author":"bodnar","year":"2020","journal-title":"Proc Robot Sci Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3040246"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref16","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"80","author":"haarnoja","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref17","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume":"80","author":"fujimoto","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2002.1258"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1561\/2300000053"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88518-4_128"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008914201877"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4271\/2013-01-2411"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509546"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2017.2676018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2017.1297735"},{"key":"ref49","article-title":"Solving Rubik’s cube with a robot hand","author":"akkaya","year":"2019","journal-title":"arXiv 1910 07113"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref46","first-page":"8198","article-title":"One solution is not all you need: Few-shot extrapolation via structured MaxEnt RL","volume":"33","author":"kumar","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref45","article-title":"Motion planning by learning the solution manifold in trajectory optimization","author":"osa","year":"2021","journal-title":"arXiv 2107 05842"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref47","article-title":"Discovering diverse solutions in deep reinforcement learning","author":"osa","year":"2021","journal-title":"arXiv 2103 07084"},{"key":"ref42","author":"achiam","year":"2018","journal-title":"Spinning up in deep reinforcement learning"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.1.108"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2958524"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920918296"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09672107.pdf?arnumber=9672107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T20:05:59Z","timestamp":1659989159000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9672107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3140781","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}