{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T02:34:42Z","timestamp":1778812482619,"version":"3.51.4"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2018,8,4]],"date-time":"2018-08-04T00:00:00Z","timestamp":1533340800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1007\/s10489-018-1241-z","type":"journal-article","created":{"date-parts":[[2018,8,4]],"date-time":"2018-08-04T04:58:46Z","timestamp":1533358726000},"page":"4889-4904","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Asynchronous reinforcement learning algorithms for solving discrete space path planning problems"],"prefix":"10.1007","volume":"48","author":[{"given":"Xingyu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shifei","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuexuan","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weikuan","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,4]]},"reference":[{"key":"1241_CR1","volume-title":"Reinforcement Learning: An introduction","author":"R Sutton","year":"1998","unstructured":"Sutton R, Barto A. (1998) Reinforcement Learning: An introduction. MIT press, Cambridge"},{"issue":"7676","key":"1241_CR2","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver D, Schrittwieser J, Simonyan K et al (2017) Mastering the game of Go without human knowledge. Nature 550(7676):354\u2013359","journal-title":"Nature"},{"issue":"7587","key":"1241_CR3","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison C et al (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529(7587):484\u2013489","journal-title":"Nature"},{"issue":"7540","key":"1241_CR4","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"1241_CR5","unstructured":"Mnih V, Kavukcuoglu K, Silver D et al (2013) Playing atari with deep reinforcement learning. Proceedings of Workshops at the 26th Neural Information Processing Systems Lake Tahoe, USA, pp 201\u2013220"},{"key":"1241_CR6","unstructured":"Levine S, Pastor P, Krizhevsky A et al (2016) Learning Hand-Eye Coordination for Robotic Grasping with Large-Scale Data Collection. International Symposium on Experimental Robotics. Springer, pp 173\u2013184"},{"key":"1241_CR7","doi-asserted-by":"crossref","unstructured":"Zhang M, Mccarthy Z, Finn C et al (2016) Learning deep neural network policies with continuous memory states. Proceedings of the International Conference on Robotics and Automation, Stockholm, pp 520-527","DOI":"10.1109\/ICRA.2016.7487174"},{"issue":"39","key":"1241_CR8","first-page":"1","volume":"17","author":"S Levine","year":"2016","unstructured":"Levine S, Finn C, Darrell T et al (2016) End-to-end training of deep visuomotor policies. J Mach Learn Res 17(39):1\u2013040","journal-title":"J Mach Learn Res"},{"key":"1241_CR9","doi-asserted-by":"crossref","unstructured":"Lenz I, Knepper R, Saxena A (2015) Deepmpc: learning deep latent features for model predictive control. Proceedings of the Robotics Science and Systems, Rome, pp 201\u2013209","DOI":"10.15607\/RSS.2015.XI.012"},{"key":"1241_CR10","unstructured":"Satija H, Pineau J (2016) Simultaneous machine translation using deep reinforcement learning. Proceedings of the Workshops of International Conference on Machine Learning, New York, pp 110\u2013119"},{"key":"1241_CR11","unstructured":"Oh J, Guo X, LEE H et al (2016) Action-conditional video prediction using deep networks in atari games. Advances in Neural Information Processing Systems, pp 2863\u20132871"},{"key":"1241_CR12","unstructured":"Guo H (2015) Generating text with deep reinforcement learning. Proceedings of the Workshops of Advances in Neural Information Processing Systems, Montreal, 1-9"},{"key":"1241_CR13","doi-asserted-by":"crossref","unstructured":"Li J, Monroe W, RITTER A et al (2016) Deep reinforcement learning for dialogue generation. Proceedings of the Conference on Empirical Methods in Natural Language Processing, Austin, pp 1192\u20131202","DOI":"10.18653\/v1\/D16-1127"},{"key":"1241_CR14","doi-asserted-by":"crossref","unstructured":"Caicedo J, Lazebnik S (2015) Active Object Localization with Deep Reinforcement Learning. IEEE international conference on computer vision. IEEE, pp 2488\u20132496","DOI":"10.1109\/ICCV.2015.286"},{"key":"1241_CR15","unstructured":"Oh J, Chockalingam V, SINGH S et al (2016) Control of memory, active perception, and action in Minecraft. Proceedings of the International Conference on Machine Learning, New York, pp 2790\u20132799"},{"key":"1241_CR16","doi-asserted-by":"crossref","unstructured":"Lample G, Chaplot D (2017) Playing FPS Games with Deep Reinforcement Learning. AAAI, pp 2140\u20132146","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"1241_CR17","doi-asserted-by":"crossref","unstructured":"Kempka M, Wydmuch M, RUNC G et al (2016) Vizdoom: A doom-based ai research platform for visual reinforcement learning. 2016 IEEE Conference Computational Intelligence and Games (CIG). IEEE, pp 1\u20138","DOI":"10.1109\/CIG.2016.7860433"},{"issue":"1","key":"1241_CR18","first-page":"9","volume":"3","author":"RS Sutton","year":"1988","unstructured":"Sutton RS (1988) Learning to predict by the methods of temporal differences. Mach Learn 3(1):9\u201344","journal-title":"Mach Learn"},{"key":"1241_CR19","volume-title":"Learning from delayed rewards","author":"C Watkins","year":"1989","unstructured":"Watkins C (1989) Learning from delayed rewards. King\u2019s College, Cambridge"},{"key":"1241_CR20","unstructured":"Rummery GA, Niranjan M (1994) On-line Q-learning using connectionist systems. University of Cambridge Department of Engineering"},{"key":"1241_CR21","unstructured":"Singh SP, Sutton RS (1996) Reinforcement learning with replacing eligibility traces. Recent Advances in Reinforcement Learning, pp 123\u2013158"},{"issue":"9","key":"1241_CR22","doi-asserted-by":"publisher","first-page":"2184","DOI":"10.1016\/j.engappai.2013.06.016","volume":"26","author":"Y Wang","year":"2013","unstructured":"Wang Y, Tzuu-Hseng SL, Chih-Jui L (2013) Backward Q-learning: The combination of Sarsa algorithm and Q-learning. Eng Appl Artif Intell 26(9):2184\u20132193","journal-title":"Eng Appl Artif Intell"},{"key":"1241_CR23","unstructured":"Mnih V, Badia AP, Mirza M et al (2016) Asynchronous methods for deep reinforcement learning. International Conference on Machine Learning, pp 1928\u20131937"},{"issue":"4","key":"1241_CR24","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1145\/122344.122377","volume":"2","author":"RS Sutton","year":"1991","unstructured":"Sutton RS (1991) Dyna, an integrated architecture for learning, planning, and reacting. ACM SIGART Bull 2(4):160\u2013163","journal-title":"ACM SIGART Bull"},{"key":"1241_CR25","unstructured":"Sutton RS, Szepesvari C, Geramifard A et al (2008) Dyna-Style Planning with linear function approximation and prioritized sweeping. Conference on Uncertainty in Artificial Intelligence"},{"key":"1241_CR26","doi-asserted-by":"crossref","unstructured":"Watkins C, Dayan P (1992) Q-learning. Machine Learning, pp 279\u2013292","DOI":"10.1007\/BF00992698"},{"key":"1241_CR27","unstructured":"Konda V, Tsitsiklis J (2000) Actor-critic algorithms. Advances in neural information pro-cessing systems, pp 1008\u20131014"},{"issue":"4","key":"1241_CR28","first-page":"168","volume":"1","author":"J Peng","year":"1993","unstructured":"Peng J, Williams RJ (1993) Efficient learning and planning within the dyna framework. Adapt Behav 1 (4):168\u2013174","journal-title":"Adapt Behav"},{"key":"1241_CR29","doi-asserted-by":"crossref","unstructured":"Wei\u00df G (2000) A multiagent variant of Dyna-Q. 2000 Proceedings International Conference on Multiagent Systems. IEEE, pp 461\u2013462","DOI":"10.1109\/ICMAS.2000.858525"},{"key":"1241_CR30","unstructured":"Skoglund A, Palm R, Duckett T (2005) Towards a supervised Dyna-Q application on a robotic manipulator. Advances in Artificial Intelligence in Sweden, pp 148\u2013153"},{"issue":"7","key":"1241_CR31","first-page":"154","volume":"26","author":"Y Zhao","year":"2009","unstructured":"Zhao Y, Chen QW, Wei-Li HU (2009) A phased dyna reinforcement learning algorithm. Comput Simul 26(7):154\u2013158","journal-title":"Comput Simul"},{"key":"1241_CR32","doi-asserted-by":"crossref","unstructured":"Wiering M, Otterlo M (2012) Reinforcement Learning: State-of-the-Art. Springer Publishing Company, Incorporated","DOI":"10.1007\/978-3-642-27645-3"},{"key":"1241_CR33","first-page":"335","volume-title":"Value-difference based exploration: adaptive control between epsilon-greedy and softmax. Annual Conference on Artificial Intelligence","author":"M Tokic","year":"2011","unstructured":"Tokic M, Palm G (2011) Value-difference based exploration: adaptive control between epsilon-greedy and softmax. Annual Conference on Artificial Intelligence. Springer, Berlin, pp 335\u2013346"},{"key":"1241_CR34","unstructured":"Nair A, Srinivasan P, Blackwell S et al (2015) Massively parallel methods for deep reinforcement learning. arXiv: 1507.04296"},{"key":"1241_CR35","unstructured":"Brockman G, Cheung V, Pettersson L et al (2016) OpenAI Gym. arXiv: 1606.01540"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10489-018-1241-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-018-1241-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-018-1241-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,28]],"date-time":"2022-08-28T19:24:44Z","timestamp":1661714684000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10489-018-1241-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,4]]},"references-count":35,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["1241"],"URL":"https:\/\/doi.org\/10.1007\/s10489-018-1241-z","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8,4]]},"assertion":[{"value":"4 August 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}