{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T22:52:50Z","timestamp":1773615170644,"version":"3.50.1"},"reference-count":24,"publisher":"Allerton Press","issue":"3","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Aut. Control Comp. Sci."],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.3103\/s0146411619030052","type":"journal-article","created":{"date-parts":[[2019,7,23]],"date-time":"2019-07-23T06:04:29Z","timestamp":1563861869000},"page":"214-222","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Playing a FPS Doom Video Game with Deep Visual Reinforcement Learning"],"prefix":"10.3103","volume":"53","author":[{"family":"Adil Khan","sequence":"first","affiliation":[]},{"given":"Feng","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Shaohui","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Ibrahim","family":"Omara","sequence":"additional","affiliation":[]}],"member":"1627","published-online":{"date-parts":[[2019,7,23]]},"reference":[{"key":"7122_CR1","first-page":"9","volume":"8","author":"Khan Adil","year":"2017","unstructured":"Khan Adil, Feng Jiang, Shaohui Liu, Worku Jifara, Zhihong Tian, and Yunsheng Fu, State-of-the-art and open challenges in RTS Game-AI and Starcraft, Int. J. Adv. Comput. Sci. Appl., 2017, vol. 8, no. 12, p. 9.","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"7122_CR2","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-77383-4_1","volume":"10736","author":"Adil Khan","year":"2017","unstructured":"Adil Khan, Kai Yang, Yunsheng Fu, Fang Lou, Worku Jifara, Feng Jiang, and Liu Shaohui, A competitive combat strategy and tactics in RTS Games AI and StarCraft, Advances in Multimedia Information Processing\u2014PCM 2017; Lect. Notes Comput. Sci., 2017, vol. 10736, pp. 3\u201312.","journal-title":"Lect. Notes Comput. Sci."},{"key":"7122_CR3","unstructured":"Wu, Y. and Tian, Y., Training agent for first-person shooter game with actor-critic curriculum learning, ICLR 2017, 2017."},{"key":"7122_CR4","doi-asserted-by":"crossref","unstructured":"Hyunsoo Park and Kyung-Joong Kim, Deep Q-Learning using redundant outputs in Visual Doom, 2016 IEEE Conference on Computational Intelligence and Games (CIG), 2016.","DOI":"10.1109\/CIG.2016.7860387"},{"key":"7122_CR5","doi-asserted-by":"crossref","unstructured":"Kempka, M., et al., ViZDoom: A Doom-based AI research platform for visual reinforcement learning, arXiv preprint arXiv:1605.02097, 2016.","DOI":"10.1109\/CIG.2016.7860433"},{"key":"7122_CR6","doi-asserted-by":"crossref","unstructured":"Khan Adil, Feng Jiang, Shaohui Liu, Grigoriev, A., Gupta, B.B., and Seungmin Rho, Training an agent for FPS Doom game using visual reinforcement learning and VizDoom, Int. J. Adv. Comput. Sci. Appl., 2017, vol. 8, no. 12.","DOI":"10.14569\/IJACSA.2017.081205"},{"key":"7122_CR7","unstructured":"Beattie, C., et al., DeepMind Lab. arXiv preprint arXiv:1612.03801, 2016."},{"key":"7122_CR8","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J. Schmidhuber","year":"2015","unstructured":"Schmidhuber, J., Deep learning in neural networks: An overview, Neural Networks, 2015, vol. 61, pp. 85\u2013117.","journal-title":"Neural Networks"},{"key":"7122_CR9","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/0893-6080(91)90009-T","volume":"4","author":"K. Hornik","year":"1991","unstructured":"Hornik, K., Approximation capabilities of multilayer feedforward networks, Neural Networks, 1991, vol. 4, no.\u00a02, pp. 251\u2013257.","journal-title":"Neural Networks"},{"key":"7122_CR10","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V. Mnih","year":"2015","unstructured":"Mnih, V., et al., Human-level control through deep reinforcement learning, Nature, 2015, vol. 518, no. 7540, pp.\u00a0529\u2013533.","journal-title":"Nature"},{"key":"7122_CR11","unstructured":"Mnih, V., et al., Playing Atari with deep reinforcement learning, arXiv preprint arXiv:1312.5602, 2013."},{"key":"7122_CR12","doi-asserted-by":"crossref","unstructured":"Lample, G. and Chaplot, D.S., Playing FPS games with deep reinforcement learning, arXiv preprint arXiv:1609.05521, 2016.","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"7122_CR13","unstructured":"Bellemare, M.G., Dabney, W., and Munos, R., A distributional perspective on reinforcement learning, arXiv preprint arXiv:1707.06887, 2017."},{"key":"7122_CR14","unstructured":"Hausknecht, M. and Stone, P., Deep recurrent Q-learning for partially observable MDPs, arXiv preprint arXiv:1507.06527, 2015."},{"key":"7122_CR15","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S. Hochreiter","year":"1997","unstructured":"Hochreiter, S. and Schmidhuber, J., Long short-term memory, Neural Comput., 1997, vol. 9, no. 8, pp. 1735\u20131780.","journal-title":"Neural Comput."},{"key":"7122_CR16","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1109\/TCIAIG.2014.2336702","volume":"7","author":"D. Wang","year":"2015","unstructured":"Wang, D. and Tan, A.-H., Creating autonomous adaptive agents in a real-time first-person shooter computer game, IEEE Trans. Comput. Intell. AI Games, 2015, vol. 7, no. 2, pp. 123\u2013138.","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"7122_CR17","first-page":"1929","volume":"15","author":"N. Srivastava","year":"2014","unstructured":"Srivastava, N., et al., Dropout: A simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., 2014, vol. 15, no. 1, pp. 1929\u20131958.","journal-title":"J. Mach. Learn. Res."},{"key":"7122_CR18","volume-title":"Lecture 6.5-RMSProp, COURSERA: Neural Networks for Machine Learning, Tech. Rep.","author":"T. Tieleman","year":"2012","unstructured":"Tieleman, T. and Hinton, G., Lecture 6.5-RMSProp, COURSERA: Neural Networks for Machine Learning, Tech. Rep., University of Toronto, 2012."},{"key":"7122_CR19","unstructured":"Schaul, T., et al., Prioritized experience replay, arXiv preprint arXiv:1511.05952, 2015."},{"key":"7122_CR20","doi-asserted-by":"crossref","unstructured":"Tokic, M., Adaptive \u03b5-greedy exploration in reinforcement learning based on value differences, Annual Conference on Artificial Intelligence, 2010.","DOI":"10.1007\/978-3-642-16111-7_23"},{"key":"7122_CR21","unstructured":"Abadi, M., et al., TensorFlow: Large-scale machine learning on heterogeneous distributed systems, arXiv preprint arXiv:1603.04467, 2016."},{"key":"7122_CR22","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1109\/JPROC.2008.917757","volume":"96","author":"J.D. Owens","year":"2008","unstructured":"Owens, J.D., Houston, M., Luebke, D., Green, S., Stone, J.E., and Phillips, J.C., GPU computing, Proc. IEEE, 2008, vol. 96, no. 5, pp. 879\u2013899.","journal-title":"Proc. IEEE"},{"key":"7122_CR23","doi-asserted-by":"crossref","unstructured":"Fairbank, M. and Alonso, E., The divergence of reinforcement learning algorithms with value-iteration and function approximation, arXiv preprint arXiv:1107.4606, 2011.","DOI":"10.1109\/IJCNN.2012.6252792"},{"key":"7122_CR24","unstructured":"Papavassiliou, V.A. and Russell, S., Convergence of reinforcement learning with general function approximators, IJCAI\u201999 Proceedings of the 16th international joint conference on Artificial intelligence, 1999, vol. 2, pp. 748\u2013755."}],"container-title":["Automatic Control and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.3103\/S0146411619030052.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.3103\/S0146411619030052","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.3103\/S0146411619030052.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T21:56:17Z","timestamp":1773611777000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.3103\/S0146411619030052"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":24,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,5]]}},"alternative-id":["7122"],"URL":"https:\/\/doi.org\/10.3103\/s0146411619030052","relation":{},"ISSN":["0146-4116","1558-108X"],"issn-type":[{"value":"0146-4116","type":"print"},{"value":"1558-108X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5]]},"assertion":[{"value":"7 May 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}