{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T14:42:41Z","timestamp":1764859361065,"version":"3.40.3"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030779382"},{"type":"electronic","value":"9783030779399"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-77939-9_18","type":"book-chapter","created":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T19:26:52Z","timestamp":1633116412000},"page":"635-667","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Playing First-Person Perspective Games with Deep Reinforcement Learning Using the State-of-the-Art Game-AI Research Platforms"],"prefix":"10.1007","author":[{"given":"Adil","family":"Khan","sequence":"first","affiliation":[]},{"given":"Asad Masood","family":"Khattak","sequence":"additional","affiliation":[]},{"given":"Muhammad Zubair","family":"Asghar","sequence":"additional","affiliation":[]},{"given":"Muhammad","family":"Naeem","sequence":"additional","affiliation":[]},{"given":"Aziz Ud","family":"Din","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,2]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Bernstein AV, Burnaev EV, Kachan ON (2018) Reinforcement learning for computer vision and robot navigation. In: International conference on machine learning and data mining in pattern recognition. Springer, Berlin","DOI":"10.1007\/978-3-319-96133-0_20"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Adil K, Jiang F, Liu S, Jifara W, Tian Z, Fu Y (2017) State-of-the-Art and open challenges in RTS Game-AI and Starcraft. (IJACSA) Int J Adv Comput Sci Appl 8(12):9","DOI":"10.14569\/IJACSA.2017.081203"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Silver D, Huang A, Maddison CJ, Guez A, Sifre L, Van Den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529(7587): 484\u2013489","DOI":"10.1038\/nature16961"},{"issue":"4","key":"18_CR4","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s12553-017-0179-1","volume":"7","author":"J Powles","year":"2017","unstructured":"Powles J, Hodson H (2017) Google DeepMind and healthcare in an age of algorithms. Heal Technol 7(4):351\u2013367","journal-title":"Heal Technol"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Khan A, Yang K, Fu Y, Lou F, Jifara W, Jiang F, Shaohui L (2017) A competitive combat strategy and tactics in RTS Games AI and StarCraft. In: Pacific Rim conference on multimedia. Springer International Publishing, Cham","DOI":"10.1007\/978-3-319-77383-4_1"},{"key":"18_CR6","unstructured":"Lyngstad A (2017) Sandbox games. A way to promote deeper learning in cross-curricular teaching? Example scenarios for classroom implementation. UiT Norges arktiske universitet"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Trenholme D, Smith SP (2008) Computer game engines for developing first-person virtual environments. Virt Real 12(3): 181\u2013187","DOI":"10.1007\/s10055-008-0092-z"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Khan A, Naeem M, Asghar MZ, Din AU, Khan A (2020) Playing first-person shooter games with machine learning techniques and methods using the VizDoom Game-AI research platform. Entertain Comput 34:100357","DOI":"10.1016\/j.entcom.2020.100357"},{"issue":"3","key":"18_CR9","doi-asserted-by":"publisher","first-page":"214","DOI":"10.3103\/S0146411619030052","volume":"53","author":"A Khan","year":"2019","unstructured":"Khan A, Jiang F, Liu S, Omara I (2019) Playing a FPS Doom video game with deep visual reinforcement learning. Autom Control Comput Sci 53(3):214\u2013222","journal-title":"Autom Control Comput Sci"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Sun Y, Khan A, Yang K, Feng J, Liu S (2019) Playing first-person-shooter games with a3c-anticipator network-based agents using reinforcement learning. In: International conference on artificial intelligence and security. Springer, Berlin","DOI":"10.1007\/978-3-030-24268-8_43"},{"key":"18_CR11","unstructured":"Hagan MT, Demuth HB, Beale MH, De Jes\u00fas O (1996) Neural network design, vol 20. Pws Pub. Boston"},{"key":"18_CR12","unstructured":"Wu Y, Tian Y (2017) Training agent for first-person shooter game with actor-critic curriculum learning. Conference paper at ICLR 2017"},{"key":"18_CR13","unstructured":"Lee S, Isaksen A, Holmg\u00e5rd C, Togelius J (2016) Predicting resource locations in-game maps using deep convolutional neural networks. In: Twelfth artificial intelligence and interactive digital entertainment conference"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Park H, Kim K-J (2016) Deep Q-Learning using Redundant Outputs.pdf. In: IEEE conference on computational intelligence and games (CIG'16)","DOI":"10.1109\/CIG.2016.7860387"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Kempka M, Wydmuch M, Runc G, Toczek J, Ja\u015bkowski W (2016) ViZDoom: a doom-based AI research platform for visual reinforcement learning. arXiv preprint arXiv:1605.02097","DOI":"10.1109\/CIG.2016.7860433"},{"key":"18_CR16","unstructured":"Ekaputra G, Lim C, Eng KI (2013) Minecraft: a game as education and scientific learning tool. In: ISICO 2013"},{"key":"18_CR17","unstructured":"Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J, Zaremba W (2016) OpenAI gym. arXiv preprint arXiv:1606.01540"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Adil K, Jiang F, Liu S, Grigorev A, Gupta BB, Rho S (2017) Training an agent for FPS doom game using visual reinforcement learning and VizDoom. (IJACSA) Int J Adv Comput Sci Appl 8(12)","DOI":"10.14569\/IJACSA.2017.081205"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"van Otterlo M, Wiering M (2012) Reinforcement learning and Markov decision processes. In: Reinforcement learning. Springer, Berlin, pp 3\u201342","DOI":"10.1007\/978-3-642-27645-3_1"},{"key":"18_CR20","unstructured":"Jin P, Keutzer K (2018) Sergey Levine. Regret minimization for partially observable deep reinforcement learning. In: International conference on machine learning"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Wydmuch M, Kempka M, Ja\u015bkowski W (2018) ViZDoom competitions: playing doom from pixels. arXiv preprint arXiv:1809.03470","DOI":"10.1109\/TG.2018.2877047"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Shao K, Zhao D, Li N, Zhu Y (2018) Learning battles in vizdoom via deep reinforcement learning. In: 2018 IEEE conference on computational intelligence and games (CIG). IEEE","DOI":"10.1109\/CIG.2018.8490423"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Shao K, Zhao D, Zhu Y, Zhang Q (2018) Visual navigation with actor-critic deep reinforcement learning. In: 2018 International joint conference on neural networks (IJCNN). IEEE","DOI":"10.1109\/IJCNN.2018.8489185"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Min B-J, Kim K-J (2017) Learning to play visual doom using model-free episodic control. In: 2017 IEEE conference on computational intelligence and games (CIG). IEEE","DOI":"10.1109\/CIG.2017.8080439"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Aitchison M (2019) Optimal use of experience in first-person shooter environments. In: 2019 IEEE conference on games (CoG). IEEE","DOI":"10.1109\/CIG.2019.8848049"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Park H, Kim K-J (2016) Deep Q-learning using redundant outputs in visual doom. In: 2016 IEEE conference on computational intelligence and games (CIG). IEEE","DOI":"10.1109\/CIG.2016.7860387"},{"key":"18_CR27","unstructured":"Romac C, B\u00e9raud V (2019) Deep Recurrent Q-Learning vs Deep Q-Learning on a simple partially observable Markov decision process with Minecraft. arXiv preprint arXiv:1903.04311"},{"key":"18_CR28","unstructured":"Johnson M, Hofmann K, Hutton T, Bignell D (2016) The Malmo platform for artificial intelligence experimentation. In: IJCAI"},{"key":"18_CR29","unstructured":"Alaniz S (2018) Deep reinforcement learning with model learning and Monte Carlo tree search in Minecraft. arXiv preprint arXiv:1803.08456"},{"key":"18_CR30","unstructured":"Oh J, Chockalingam V, Singh S, Lee H (2016) Control of memory, active perception, and action in Minecraft. arXiv preprint arXiv:1605.09128"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Mathisen T, Oliver A, Cohen T, Schulman J (2019) Teacher-student curriculum learning. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2019.2934906"},{"key":"18_CR32","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347"},{"key":"18_CR33","unstructured":"Garmulewicz M, Michalewski H, Mi\u0142o\u015b P (2018) Expert-augmented actor-critic for ViZDoom and Montezumas Revenge. arXiv preprint arXiv:1809.03447"},{"key":"18_CR34","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 (2015) Deep learning in neural networks: an overview. Neural Netw 61:85\u2013117","journal-title":"Neural Netw"},{"issue":"2","key":"18_CR35","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 (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4(2):251\u2013257","journal-title":"Neural Netw"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","DOI":"10.1038\/nature14236"},{"key":"18_CR37","unstructured":"Lample G, Singh DC (2016) Playing FPS games with deep reinforcement learning. arXiv preprint arXiv:1609.05521"},{"key":"18_CR38","unstructured":"Bellemare MG, Dabney W, Munos R (2017) A distributional perspective on reinforcement learning. arXiv preprint arXiv:1707.06887"},{"key":"18_CR39","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2015) Prioritized experience replay. arXiv preprint arXiv:1511.05952"},{"key":"18_CR40","unstructured":"Hausknecht M, Stone P (2015) Deep recurrent q-learning for partially observable mdps. CoRR, abs\/1507.06527"},{"issue":"8","key":"18_CR41","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, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"18_CR42","unstructured":"Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958"},{"key":"18_CR43","unstructured":"Hafner D (2016) Deep reinforcement learning from raw pixels in doom. arXiv preprint arXiv:1610.02164"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Khan A, Feng J, Liu S, Asghar MZ (2019) Optimal skipping rates: training agents with fine-grained control using deep reinforcement learning. J Robot 2019:10","DOI":"10.1155\/2019\/2970408"},{"key":"18_CR45","unstructured":"Lee L, Parisotto E, Chaplot DS, Salakhutdinov R (2018) LSTM iteration networks: an exploration of differentiable path finding"},{"key":"18_CR46","unstructured":"Tieleman T, Hinton G (2012) Lecture 6.5-RMSProp, COURSERA: neural networks for machine learning. University of Toronto, Technical Report"},{"key":"18_CR47","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467"},{"key":"18_CR48","unstructured":"Bradski, Gary and Adrian Kaehler, OpenCV. Dr. Dobb\u2019s journal of software tools, 2000. 3."},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Owens JD, Houston M, Luebke D, Green S, Stone JE, Phillips JC (2008) GPU computing. Proc IEEE 96(5):879\u2013899","DOI":"10.1109\/JPROC.2008.917757"},{"key":"18_CR50","doi-asserted-by":"crossref","unstructured":"Fairbank M, Alonso E (2011)The divergence of reinforcement learning algorithms with value-iteration and function approximation. arXiv preprint arXiv:1107.4606","DOI":"10.1109\/IJCNN.2012.6252792"},{"key":"18_CR51","unstructured":"Papavassiliou VA, Russell S (1999) Convergence of reinforcement learning with general function approximators. IJCAI"},{"key":"18_CR52","unstructured":"Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747"},{"key":"18_CR53","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602"},{"key":"18_CR54","unstructured":"Kingma DP, Jimmy Ba A (2014) A method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"18_CR55","unstructured":"Koenig S, Reid Simmons X (1998) A robot navigation architecture based on partially observable Markov decision process models. In: Artificial intelligence based mobile robotics: case studies of successful robot systems, pp 91\u2013122"}],"container-title":["Studies in Computational Intelligence","Deep Learning for Unmanned Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-77939-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T06:13:05Z","timestamp":1725862385000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-77939-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030779382","9783030779399"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-77939-9_18","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"type":"print","value":"1860-949X"},{"type":"electronic","value":"1860-9503"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}