{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:02:13Z","timestamp":1730268133744,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T00:00:00Z","timestamp":1626825600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T00:00:00Z","timestamp":1626825600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T00:00:00Z","timestamp":1626825600000},"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":[[2021,7,21]]},"DOI":"10.1109\/indin45523.2021.9557543","type":"proceedings-article","created":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T21:23:04Z","timestamp":1633987384000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Deep Reinforcement Learning with Adjustments"],"prefix":"10.1109","author":[{"given":"Hamed","family":"Khorasgani","sequence":"first","affiliation":[]},{"given":"Haiyan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chetan","family":"Gupta","sequence":"additional","affiliation":[]},{"given":"Susumu","family":"Serita","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"5690","article-title":"Imagination-augmented agents for deep reinforcement learning","author":"racani\u00e8re","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"haarnoja","key":"ref11"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref12"},{"key":"ref13","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"article-title":"Stable baselines","year":"2018","author":"hill","key":"ref15"},{"article-title":"World models","year":"2018","author":"ha","key":"ref16"},{"article-title":"Model-based value expansion for efficient model-free reinforcement learning","year":"2018","author":"feinberg","key":"ref17"},{"key":"ref18","first-page":"8224","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","author":"buckman","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-0348-0439-4_11"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"article-title":"Challenges of real-world reinforcement learning","year":"2019","author":"dulac-arnold","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(02)00272-8"},{"article-title":"Safe exploration in continuous action spaces","year":"2018","author":"dalal","key":"ref5"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref8"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","year":"2017","author":"silver","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90002-2"},{"key":"ref9","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","start":{"date-parts":[[2021,7,21]]},"location":"Palma de Mallorca, Spain","end":{"date-parts":[[2021,7,23]]}},"container-title":["2021 IEEE 19th International Conference on Industrial Informatics (INDIN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9557349\/9557353\/09557543.pdf?arnumber=9557543","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:46:50Z","timestamp":1652197610000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9557543\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,21]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/indin45523.2021.9557543","relation":{},"subject":[],"published":{"date-parts":[[2021,7,21]]}}}