{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T03:21:44Z","timestamp":1730344904134,"version":"3.28.0"},"reference-count":8,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T00:00:00Z","timestamp":1662422400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T00:00:00Z","timestamp":1662422400000},"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":[],"published-print":{"date-parts":[[2022,9,6]]},"DOI":"10.23919\/sice56594.2022.9905810","type":"proceedings-article","created":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T15:43:18Z","timestamp":1665070998000},"page":"141-145","source":"Crossref","is-referenced-by-count":0,"title":["Disturbance Observable Reinforcement Learning that Compensates for Changes in Environment"],"prefix":"10.23919","author":[{"given":"SeongIn","family":"Kim","sequence":"first","affiliation":[{"name":"University of Tsukuba,Master’s Program in Intelligent and Mechanical Interaction Systems,Ibaraki,Japan"}]},{"given":"Takeshi","family":"Shibuya","sequence":"additional","affiliation":[{"name":"University of Tsukuba,Faculty of Engineering, Information and Systems,Ibaraki,Japan"}]}],"member":"263","reference":[{"key":"ref4","first-page":"6215","article-title":"Action Robust Reinforcement Learning and Applications in Continuous Control","volume":"97","author":"tessler","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09997-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref5","first-page":"2817","article-title":"Robust Adversarial Reinforcement Learning","author":"pinto","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref8","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref7","first-page":"336","article-title":"Safe Reinforcement Learning of Control-Affine Systems with Vertex Networks","author":"zheng","year":"2021","journal-title":"Proceedings of the 3rd Conference on Learning for Dynamics and Control"},{"key":"ref2","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"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"}],"event":{"name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","start":{"date-parts":[[2022,9,6]]},"location":"Kumamoto, Japan","end":{"date-parts":[[2022,9,9]]}},"container-title":["2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9905734\/9905735\/09905810.pdf?arnumber=9905810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T15:24:36Z","timestamp":1669649076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9905810\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,6]]},"references-count":8,"URL":"https:\/\/doi.org\/10.23919\/sice56594.2022.9905810","relation":{},"subject":[],"published":{"date-parts":[[2022,9,6]]}}}