{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T09:50:56Z","timestamp":1730281856075,"version":"3.28.0"},"reference-count":7,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,7]],"date-time":"2022-06-07T00:00:00Z","timestamp":1654560000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,7]],"date-time":"2022-06-07T00:00:00Z","timestamp":1654560000000},"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":[[2022,6,7]]},"DOI":"10.1109\/meco55406.2022.9797177","type":"proceedings-article","created":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T19:47:45Z","timestamp":1655840865000},"page":"1-4","source":"Crossref","is-referenced-by-count":3,"title":["Testing reward function choice influence on training performance of Double DQN"],"prefix":"10.1109","author":[{"given":"Stefan","family":"Scepanovic","sequence":"first","affiliation":[{"name":"University of Montenegro,Faculty of Electrical Engineering,Podgorica,Montenegro"}]}],"member":"263","reference":[{"journal-title":"Openai com","article-title":"Gym: A toolkit for developing and comparing reinforcement learning algorithms","year":"2016","key":"ref4"},{"journal-title":"Deep reinforcement learning An overview","year":"2018","author":"li","key":"ref3"},{"journal-title":"Pytorch org","article-title":"SmoothL1Loss — PyTorch 1.8.1 documentation","year":"0","key":"ref6"},{"key":"ref5","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"},{"key":"ref7","article-title":"How Does Learning Rate Decay Help Modern Neural Networks?","author":"you","year":"2019","journal-title":"ArXiv org"},{"key":"ref2","first-page":"219","article-title":"An Introduction to Deep Reinforcement Learning. Foundations and Trends®","volume":"11","author":"fran\u00e7ois-lavot","year":"2018","journal-title":"Machine Learning"},{"key":"ref1","article-title":"Hands-on machine learning with Scikit-Learn and Tensor Flow concepts, tools, and techniques to build intelligent systems","author":"g\u00e9ron","year":"2019","journal-title":"O'Reilly Media Inc"}],"event":{"name":"2022 11th Mediterranean Conference on Embedded Computing (MECO)","start":{"date-parts":[[2022,6,7]]},"location":"Budva, Montenegro","end":{"date-parts":[[2022,6,10]]}},"container-title":["2022 11th Mediterranean Conference on Embedded Computing (MECO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9797068\/9797069\/09797177.pdf?arnumber=9797177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T19:36:27Z","timestamp":1658432187000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9797177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,7]]},"references-count":7,"URL":"https:\/\/doi.org\/10.1109\/meco55406.2022.9797177","relation":{},"subject":[],"published":{"date-parts":[[2022,6,7]]}}}