{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T14:42:53Z","timestamp":1764859373653,"version":"3.40.3"},"publisher-location":"Cham","reference-count":61,"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_15","type":"book-chapter","created":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T19:26:52Z","timestamp":1633116412000},"page":"503-562","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Playing Doom with Anticipator-A3C Based Agents Using Deep Reinforcement Learning and the ViZDoom Game-AI Research Platform"],"prefix":"10.1007","author":[{"given":"Adil","family":"Khan","sequence":"first","affiliation":[]},{"given":"Muhammad","family":"Naeem","sequence":"additional","affiliation":[]},{"given":"Asad Masood","family":"Khattak","sequence":"additional","affiliation":[]},{"given":"Muhammad Zubair","family":"Asghar","sequence":"additional","affiliation":[]},{"given":"Abdul Haseeb","family":"Malik","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,2]]},"reference":[{"key":"15_CR1","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 2017. Springer International Publishing, Cham","DOI":"10.1007\/978-3-319-77383-4_1"},{"issue":"1","key":"15_CR2","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1109\/TCIAIG.2014.2365414","volume":"8","author":"M Stanescu","year":"2016","unstructured":"Stanescu M, \u010certick\u00fd M (2016) Predicting opponent\u2019s production in real-time strategy games with answer set programming. IEEE Trans Comput Intell AI Games 8(1):89\u201394","journal-title":"IEEE Trans Comput Intell AI Games"},{"key":"15_CR3","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"},{"issue":"2","key":"15_CR4","first-page":"279","volume":"23","author":"M Asada","year":"1996","unstructured":"Asada M, Noda S, Tawaratsumida S, Hosoda K (1996) Purposive behavior acquisition for a real robot by vision-based reinforcement learning. Mach Learn 23(2):279\u2013303","journal-title":"Mach Learn"},{"key":"15_CR5","unstructured":"Daylamani-Zad D, Graham LB, Paraskevopoulos IT. Chain of command in autonomous cooperative agents for battles in real-time strategy games. J Comput Educ:1\u201332"},{"key":"15_CR6","unstructured":"McCorduck P (2009) Machines who think: a personal inquiry into the history and prospects of artificial intelligence. AK Peters\/CRC Press"},{"key":"15_CR7","unstructured":"McCorduck P, Minsky M, Selfridge OG, Simon HA (1977) History of artificial intelligence. IJCAI"},{"key":"15_CR8","unstructured":"Beattie C, Leibo JZ, Teplyashin D, Ward T, Wainwright M, K\u00fcttler H, Lefrancq A, Green S, Vald\u00e9s V, Sadik A (2016) DeepMind Lab. arXiv:1612.03801"},{"key":"15_CR9","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"},{"key":"15_CR10","unstructured":"Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J, Zaremba W (2016) OpenAI gym. arXiv:1606.01540"},{"key":"15_CR11","unstructured":"Buchanan BG (2005) A (very) brief history of artificial intelligence. Ai Mag 26(4):53"},{"key":"15_CR12","unstructured":"Michalski RS, Carbonell JG, Mitchell TM (2013) Machine learning: an artificial intelligence approach. Springer Science & Business Media"},{"key":"15_CR13","unstructured":"Stanescu M, Hernandez SP, Erickson G, Greiner R, Buro M (2013) Predicting army combat outcomes in starcraft. AIIDE. Citeseer"},{"key":"15_CR14","unstructured":"Russell SJ, Norvig P (2016) Artificial intelligence: a modern approach. Pearson Education Limited, Malaysia"},{"key":"15_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:1605.02097","DOI":"10.1109\/CIG.2016.7860433"},{"key":"15_CR16","unstructured":"DeepMind, David Silver and Google (2015) Deep reinforcement learning. In: Keynote for ICLR, 2015. San Diego, CA, USA"},{"key":"15_CR17","unstructured":"Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning, vol 1. MIT press Cambridge"},{"key":"15_CR18","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"},{"key":"15_CR19","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction, vol 1. MIT press Cambridge"},{"key":"15_CR20","unstructured":"Packer C, Gao K, Kos J, Kr\u00e4henb\u00fchl P, Koltun V, Song D (2018) Assessing generalization in deep reinforcement learning. arXiv:1810.12282"},{"key":"15_CR21","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. Entertainment Comput 34:100357","DOI":"10.1016\/j.entcom.2020.100357"},{"key":"15_CR22","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing Atari with deep reinforcement learning. arXiv:1312.5602"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Van Hasselt H, Guez A, Silver D (2015) Deep reinforcement learning with double Q-learning. AAAI","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"15_CR24","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2015) Prioritized experience replay. arXiv:1511.05952"},{"key":"15_CR25","unstructured":"Wang Z, Schaul T, Hessel M, Van Hasselt H, Lanctot M, De Freitas N (2015) Dueling network architectures for deep reinforcement learning. arXiv:1511.06581"},{"key":"15_CR26","unstructured":"Mnih V, Badia AP, Mirza M, Graves A, Lillicrap T, Harley T, Silver D, Kavukcuoglu K (2016) Asynchronous methods for deep reinforcement learning. In: International conference on machine learning"},{"key":"15_CR27","unstructured":"Jaderberg M, Mnih V, Czarnecki WM, Schaul T, Leibo JZ, Silver D, Kavukcuoglu K (2016) Reinforcement learning with unsupervised auxiliary tasks. arXiv:1611.05397"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Stanescu M, Barriga NA, Hess A, Buro M (2016) Evaluating real-time strategy game states using convolutional neural networks, Sept 2016","DOI":"10.1109\/CIG.2016.7860439"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Chaplot DS, Lample G (2017) Arnold: an autonomous agent to play FPS games. AAAI","DOI":"10.1609\/aaai.v31i1.10534"},{"issue":"3","key":"15_CR30","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":"15_CR31","doi-asserted-by":"crossref","unstructured":"Graves A (2012) Supervised sequence labelling with recurrent neural networks. ISBN 9783642212703. http:\/\/books.google.com\/books","DOI":"10.1007\/978-3-642-24797-2"},{"key":"15_CR32","unstructured":"Wu Y, Tian Y (2017) Training agent for first-person shooter game with actor-critic curriculum learning. In: Conference paper at ICLR 2017"},{"key":"15_CR33","unstructured":"Justesen N, Bontrager P, Togelius J, Risi S (2017) Deep learning for video game playing. arXiv:1708.07902"},{"key":"15_CR34","unstructured":"Li O, Liu H, Chen C, Rudin C (2017) Deep learning for case-based reasoning through prototypes: a neural network that explains its predictions. arXiv:1710.04806"},{"key":"15_CR35","unstructured":"Hagan MT, Demuth HB, Beale MH, De Jes\u00fas O (1996) Neural network design, vol 20. PWS Publication. Boston"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Widrow B, Lehr MA (1990) 30 years of adaptive neural networks: perceptron, Madaline, and backpropagation. Proc IEEE 78(9):1415\u20131442","DOI":"10.1109\/5.58323"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Gardner MW, Dorling SR (1998) Artificial neural networks (the multilayer perceptron)\u2014a review of applications in the atmospheric sciences. Atmosph Environ 32(14\u201315):2627\u20132636","DOI":"10.1016\/S1352-2310(97)00447-0"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Nowlan SJ, Hinton GE (1992) Simplifying neural networks by soft weight-sharing. Neural Comput 4(4):473\u2013493","DOI":"10.1162\/neco.1992.4.4.473"},{"issue":"1","key":"15_CR39","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0893-6080(89)90014-2","volume":"2","author":"P Baldi","year":"1989","unstructured":"Baldi P, Hornik K (1989) Neural networks and principal component analysis: learning from examples without local minima. Neural Netw 2(1):53\u201358","journal-title":"Neural Netw"},{"key":"15_CR40","unstructured":"Thrun S, Pratt L (2012) Learning to learn. Springer Science & Business Media"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Lu H, Plataniotis KN, Venetsanopoulos AN (2011) A survey of multilinear subspace learning for tensor data. Pattern Recogn 44(7):1540\u20131551","DOI":"10.1016\/j.patcog.2011.01.004"},{"key":"15_CR42","unstructured":"Karlik B, Olgac AV (2011) Performance analysis of various activation functions in generalized MLP architectures of neural networks. Int J Artif Intell Exp Syst 1(4):111\u2013122"},{"key":"15_CR43","unstructured":"Farhadi F (2017) Learning activation functions in deep neural networks. \u00c9cole Polytechnique de Montr\u00e9al"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"van Otterlo M, Wiering M (2012) Reinforcement learning and Markov decision processes. In: Reinforcement learning. Springer, pp 3\u201342","DOI":"10.1007\/978-3-642-27645-3_1"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Kaelbling LP, Littman ML, Moore AW (1996) Reinforcement learning: a survey. J Artif Intell Res 4:237\u2013285","DOI":"10.1613\/jair.301"},{"key":"15_CR46","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":"15_CR47","doi-asserted-by":"crossref","unstructured":"Wang Q, Clarke RJ (1992) Motion estimation and compensation for image sequence coding. Signal Process Image Commun 4(2):161\u2013174","DOI":"10.1016\/0923-5965(92)90022-8"},{"key":"15_CR48","doi-asserted-by":"crossref","unstructured":"Kappagantula S, Rao K (1985) Motion-compensated interframe image prediction. IEEE Trans Commun 33(9):1011\u20131015","DOI":"10.1109\/TCOM.1985.1096415"},{"key":"15_CR49","unstructured":"Zhou, Bingpeng and Qingchun Chen, A tutorial on Minimum Mean Square Error Estimation. 2015, jan."},{"key":"15_CR50","doi-asserted-by":"crossref","unstructured":"Brunet D, Vrscay ER, Wang Z (2012) On the mathematical properties of the structural similarity index. IEEE Trans Image Process 21(4):1488\u20131499","DOI":"10.1109\/TIP.2011.2173206"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Korhonen J, You J (2012) Peak signal-to-noise ratio revisited: Is simple beautiful? In: 2012 fourth international workshop on quality of multimedia experience (QoMEX). IEEE","DOI":"10.1109\/QoMEX.2012.6263880"},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Mandic DP, Chambers J (2001) Recurrent neural networks for prediction: learning algorithms, architectures and stability. Wiley","DOI":"10.1002\/047084535X"},{"key":"15_CR53","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:1603.04467"},{"key":"15_CR54","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":"15_CR55","unstructured":"Jouppi NP, Young C, Patil N, Patterson D, Agrawal G, Bajwa R, Bates S, Bhatia S, Boden N, Borchers A (2017) In-datacenter performance analysis of a tensor processing unit. In: 2017 ACM\/IEEE 44th annual international symposium on computer architecture (ISCA). IEEE"},{"key":"15_CR56","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":"15_CR57","unstructured":"Freitas S, Dudley A, Gopalakrishnan S, Feinglass J, Clayton B (2018) Exploration of DQN in ViZDoom"},{"key":"15_CR58","unstructured":"Adamsson M (2018) Curriculum learning for increasing the performance of a reinforcement learning agent in a static first-person shooter game"},{"key":"15_CR59","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1155\/2013\/492852","volume":"2013","author":"V Uc-Cetina","year":"2013","unstructured":"Uc-Cetina V (2013) A novel reinforcement learning architecture for continuous state and action spaces. Adv Artif Intell 2013:7","journal-title":"Adv Artif Intell"},{"key":"15_CR60","unstructured":"Bradski G, Kaehler A (2000) OpenCV. Dr. Dobb\u2019s J Softw Tools 3"},{"key":"15_CR61","unstructured":"Dosovitskiy A, Koltun V (2016) Learning to act by predicting the future. arXiv:1611.01779"}],"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_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T23:47:39Z","timestamp":1673394459000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-77939-9_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030779382","9783030779399"],"references-count":61,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-77939-9_15","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"}}]}}