{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T03:32:54Z","timestamp":1730259174944,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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":[[2019,10]]},"DOI":"10.1109\/icstcc.2019.8885715","type":"proceedings-article","created":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:03:58Z","timestamp":1572566638000},"page":"860-865","source":"Crossref","is-referenced-by-count":1,"title":["A Comparative Performance Study of Reinforcement Learning Algorithms for a Continuous Space Problem"],"prefix":"10.1109","author":[{"given":"Andreea-Iulia","family":"Patachi","sequence":"first","affiliation":[]},{"given":"Florin","family":"Leon","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Reinforcement learning through asynchronous advantage actor-critic on a gpu","author":"babaeizadeh","year":"2016","journal-title":"arXiv preprint arXiv 1611 06256"},{"key":"ref12","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref13","article-title":"Imagination-augmented agents for deep reinforcement learning","author":"racani\u00e8re","year":"2017","journal-title":"Advances in neural information processing systems"},{"journal-title":"An open-source machine learning framework for everyone","year":"0","key":"ref14"},{"journal-title":"Keras The Python deep learning library","year":"0","key":"ref15"},{"journal-title":"The Microsoft Cognitive Toolkit (CNTK) An open-source toolkit for commercial-grade distributed deep learning","year":"0","key":"ref16"},{"journal-title":"Theano A Python library","year":"0","key":"ref17"},{"journal-title":"Efficient memory-based learning for robot control","year":"1990","author":"moore","key":"ref18"},{"journal-title":"RL-Library","year":"2010","key":"ref19"},{"key":"ref4","article-title":"Deep reinforcement learning for robotic manipulation-the state of the art","author":"amarjyoti","year":"2017","journal-title":"arXiv preprint arXiv 1701 08878"},{"key":"ref3","first-page":"279","article-title":"Q-learning. Machine learning","volume":"8","author":"watkins","year":"1992","journal-title":"Kluwer Academic Publishers"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/337"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"journal-title":"Q-learning Machine Learning","year":"1989","author":"watkins","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref2","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref1","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref20","article-title":"Autonomous Transfer for Reinforcement Learning","author":"taylor","year":"2008","journal-title":"Proc Int Joint Conf Autonomous Agents and Multiagent Systems"},{"journal-title":"Advanced multi-agent fuzzy reinforcement learning","year":"2004","author":"naeeni","key":"ref22"},{"key":"ref21","first-page":"123","volume":"22","author":"singh","year":"1996","journal-title":"Reinforcement learning with replacing eligibility traces Machine learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/11527862_14"},{"journal-title":"Intelligent Agent Planning with Quasi-Determined States Using Inductive Learning","year":"2010","author":"leon","key":"ref23"}],"event":{"name":"2019 23rd International Conference on System Theory, Control and Computing (ICSTCC)","start":{"date-parts":[[2019,10,9]]},"location":"Sinaia, Romania","end":{"date-parts":[[2019,10,11]]}},"container-title":["2019 23rd International Conference on System Theory, Control and Computing (ICSTCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8880038\/8885414\/08885715.pdf?arnumber=8885715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:08:04Z","timestamp":1657854484000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8885715\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icstcc.2019.8885715","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}