{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T10:36:25Z","timestamp":1778495785970,"version":"3.51.4"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,12]],"date-time":"2021-09-12T00:00:00Z","timestamp":1631404800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,12]],"date-time":"2021-09-12T00:00:00Z","timestamp":1631404800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,12]],"date-time":"2021-09-12T00:00:00Z","timestamp":1631404800000},"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":[[2021,9,12]]},"DOI":"10.1109\/ccece53047.2021.9569056","type":"proceedings-article","created":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T21:13:38Z","timestamp":1635282818000},"page":"1-7","source":"Crossref","is-referenced-by-count":92,"title":["Reinforcement Learning Algorithms: An Overview and Classification"],"prefix":"10.1109","author":[{"given":"Fadi","family":"AlMahamid","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katarina","family":"Grolinger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"2408","article-title":"Optimizing neural networks with kronecker-factored approximate curvature","author":"martens","year":"2015","journal-title":"Int Conference on Machine Learning"},{"key":"ref32","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","author":"wu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Safe and efficient off-policy reinforcement learning","author":"munos","year":"2016","journal-title":"arXiv 1606 02647"},{"key":"ref30","article-title":"Sample efficient actor-critic with experience replay","author":"wang","year":"0","journal-title":"arXiv 1611 01224 2016"},{"key":"ref35","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"Int Conference on Machine Learning"},{"key":"ref34","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Int Conference on Machine Learning"},{"key":"ref10","first-page":"2094","article-title":"Deep reinforcement learning with double Q-Learning","author":"van hasselt","year":"2016","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref11","first-page":"2939","article-title":"Dueling Network Architectures for Deep Reinforcement Learning","volume":"4","author":"wang","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref12","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"0","journal-title":"arXiv 1507 06527 2015"},{"key":"ref13","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref14","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Int Conference on Machine Learning"},{"key":"ref15","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref17","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref19","article-title":"Decoupling value and policy for generalization in reinforcement learning","author":"raileanu","year":"0","journal-title":"arXiv 2102 10330 2021"},{"key":"ref28","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Int Conference on Machine Learning"},{"key":"ref4","article-title":"Prioritized experience replay","author":"schaul","year":"0","journal-title":"arXiv 1511 05952 2015"},{"key":"ref27","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"0","journal-title":"arXiv 1706 02275 2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref6","article-title":"On-line Q-learning using connectionist systems","volume":"37","author":"rummery","year":"1994","journal-title":"University of Cambridge"},{"key":"ref29","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971172"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7849837"},{"key":"ref2","first-page":"1","article-title":"Self-driving cars using cnn and q-learning","author":"chishti","year":"2018","journal-title":"IEEE 21st International Multi-Topic Conference"},{"key":"ref9","first-page":"1","article-title":"Double Q-learning","author":"van hasselt","year":"2010","journal-title":"Advances in Neural Information Processing Systems 23 24th Annual Conference on Neural Information Processing Systems 2010"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICoIAS.2018.8494053"},{"key":"ref20","article-title":"Stein variational policy gradient","author":"liu","year":"0","journal-title":"arXiv 1704 02399 2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/app9245571"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"0","journal-title":"arXiv 1707 06347 2017"},{"key":"ref24","article-title":"Stein variational gradient descent: A general purpose bayesian inference algorithm","author":"liu","year":"0","journal-title":"arXiv 1608 04471 2016"},{"key":"ref23","article-title":"Phasic policy gradient","author":"cobbe","year":"0","journal-title":"arXiv 2009 04416 2020"},{"key":"ref26","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"0","journal-title":"arXiv 1804 08617 2018"},{"key":"ref25","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"arXiv 1509 02971 2015"}],"event":{"name":"2021 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","location":"ON, Canada","start":{"date-parts":[[2021,9,12]]},"end":{"date-parts":[[2021,9,17]]}},"container-title":["2021 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9569025\/9569028\/09569056.pdf?arnumber=9569056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:53:32Z","timestamp":1652201612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9569056\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,12]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/ccece53047.2021.9569056","relation":{},"subject":[],"published":{"date-parts":[[2021,9,12]]}}}