{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:26:13Z","timestamp":1774628773457,"version":"3.50.1"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031184604","type":"print"},{"value":"9783031184611","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-18461-1_11","type":"book-chapter","created":{"date-parts":[[2022,10,12]],"date-time":"2022-10-12T07:15:14Z","timestamp":1665558914000},"page":"165-184","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A Survey of\u00a0Reinforcement Learning Toolkits for\u00a0Gaming: Applications, Challenges and\u00a0Trends"],"prefix":"10.1007","author":[{"given":"Charitha Sree","family":"Jayaramireddy","sequence":"first","affiliation":[]},{"given":"Sree Veera Venkata Sai Saran","family":"Naraharisetti","sequence":"additional","affiliation":[]},{"given":"Mohamad","family":"Nassar","sequence":"additional","affiliation":[]},{"given":"Mehdi","family":"Mekni","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,13]]},"reference":[{"key":"11_CR1","unstructured":"AlphaZero: shedding new light on chess, shogi, and go. https:\/\/deepmind.com\/blog\/article\/alphazero-shedding-new-light-grand-games-chess-shogi-and-go"},{"key":"11_CR2","unstructured":"Facebook, Carnegie Mellon build first AI that beats pros in 6-player poker. https:\/\/ai.facebook.com\/blog\/pluribus-first-ai-to-beat-pros-in-6-player-poker\/"},{"key":"11_CR3","unstructured":"MIT 6.S191: Introduction to deep learning. https:\/\/introtodeeplearning.com\/"},{"key":"11_CR4","unstructured":"OpenAI"},{"key":"11_CR5","unstructured":"OpenAI five defeats dota 2 world champions. https:\/\/openai.com\/blog\/openai-five-defeats-dota-2-world-champions\/"},{"key":"11_CR6","unstructured":"Unity machine learning agents"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Arulkumaran, K., Cully, A., Togelius, J. : Alphastar: an evolutionary computation perspective. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, pp. 314\u2013315 (2019)","DOI":"10.1145\/3319619.3321894"},{"issue":"6S3","key":"11_CR8","first-page":"193","volume":"7","author":"N Baby","year":"2019","unstructured":"Baby, N., Goswami, B.: Implementing artificial intelligence agent within connect 4 using unity3D and machine learning concepts. Int. J. Recent Technol. Eng. 7(6S3), 193\u2013200 (2019)","journal-title":"Int. J. Recent Technol. Eng."},{"key":"11_CR9","unstructured":"Barth-Maron G., et al.: Distributed distributional deterministic policy gradients. arXiv preprint arXiv:1804.08617, 2018"},{"key":"11_CR10","unstructured":"Bellemare, M. G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. In: International Conference on Machine Learning, pp. 449\u2013458. PMLR (2017)"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Bertens, P., Guitart, A., Chen, P. P., Peri\u00e1\u00f1ez, \u00c1.: A machine-learning item recommendation system for video games. In: 2018 IEEE Conference on Computational Intelligence and Games (CIG), pp. 1\u20134. IEEE (2018)","DOI":"10.1109\/CIG.2018.8490456"},{"key":"11_CR12","unstructured":"Booth J., Booth, J.: Marathon environments: multi-agent continuous control benchmarks in a modern video game engine. arXiv preprint arXiv:1902.09097 (2019)"},{"key":"11_CR13","unstructured":"Bornemark, O.: Success factors for e-sport games. In: Ume\u00e5\u2019s 16th Student Conference in Computing Science, pp. 1\u201312 (2013)"},{"key":"11_CR14","unstructured":"Borovikov, I., Harder, J., Sadovsky, M., Beirami, A.: Towards interactive training of non-player characters in video games. arXiv preprint arXiv:1906.00535 (2019)"},{"key":"11_CR15","first-page":"21","volume":"7","author":"M Borowy","year":"2013","unstructured":"Borowy, M., et al.: Pioneering eSport: the experience economy and the marketing of early 1980s arcade gaming contests. Int. J. Commun. 7, 21 (2013)","journal-title":"Int. J. Commun."},{"key":"11_CR16","unstructured":"Brockman, G., et al.:Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Cao, Z., Lin, C. -T.: Reinforcement learning from hierarchical critics. IEEE Trans. Neural Netw. Learn. Syst. (2021)","DOI":"10.1109\/TNNLS.2021.3103642"},{"key":"11_CR18","unstructured":"Castro, P. S., Moitra, S., Gelada, C., Kumar, S., Bellemare, M. G.: A Research framework for deep reinforcement learning, dopamine (2018)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Dabney, W., Ostrovski, G., Silver, D., Munos, R.: Implicit quantile networks for distributional reinforcement learning. In: International conference on machine learning, pages 1096\u20131105. PMLR (2018)","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"11_CR20","unstructured":"Dhariwal, P., et al.: OpenAI Baselines, Szymon Sidor (2022)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Frank, A. B.: Gaming AI without AI. J. Defense Mod. Simul., p. 15485129221074352 (2022)","DOI":"10.1177\/15485129221074352"},{"key":"11_CR22","unstructured":"Moreno, S. E. G., Montalvo, J. A. C., Palma-Ruiz, J. M.: La industria cultural y la industria de los videojuegos. JUEGOS Y SOCIEDAD: DESDE LA INTERACCI\u00d3N A LA INMERSI\u00d3N PARA EL CAMBIO SOCIAL, pp. 19\u201326 (2019)"},{"key":"11_CR23","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning. In: Thirty-second AAAI conference on artificial intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"11_CR25","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. Adv. Neural Info. Proc. Syst. 29 (2016)"},{"key":"11_CR26","unstructured":"Juliani, A., et al.: Unity: a general platform for intelligent agents. arXiv preprint arXiv:1809.02627 (2018)"},{"key":"11_CR27","volume-title":"Learn Unity ML-Agents-Fundamentals of Unity Machine Learning: Incorporate New Powerful ML Algorithms Such as Deep Reinforcement Learning for Games","author":"M Lanham","year":"2018","unstructured":"Lanham, M.: Learn Unity ML-Agents-Fundamentals of Unity Machine Learning: Incorporate New Powerful ML Algorithms Such as Deep Reinforcement Learning for Games. Packt Publishing Ltd., Birmingham (2018)"},{"key":"11_CR28","volume-title":"Good Luck Have Fun: The Rise of eSports","author":"R Li","year":"2017","unstructured":"Li, R.: Good Luck Have Fun: The Rise of eSports. Simon and Schuster, New York (2017)"},{"key":"11_CR29","unstructured":"Lillicrap, T. P.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"11_CR30","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. arXiv preprint arXiv:1706.02275 (2017)"},{"key":"11_CR31","doi-asserted-by":"publisher","unstructured":"Lyle, D., et al.: Chess and strategy in the age of artificial intelligence. In: Lai, D. (eds) US-China Strategic Relations and Competitive Sports, pages 87\u2013126. Palgrave Macmillan, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-92200-9_5","DOI":"10.1007\/978-3-030-92200-9_5"},{"issue":"9","key":"11_CR32","doi-asserted-by":"publisher","first-page":"455","DOI":"10.4236\/jsea.2021.149027","volume":"14","author":"M Mekni","year":"2021","unstructured":"Mekni, M.: An artificial intelligence based virtual assistant using conversational agents. J. Softw. Eng. Appl. 14(9), 455\u2013473 (2021)","journal-title":"J. Softw. Eng. Appl."},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Mekni, M., Jayan, A.: Automated modular invertebrate research environment using software embedded systems. In: Proceedings of the 2nd International Conference on Software Engineering and Information Management, pp. 85\u201390 (2019)","DOI":"10.1145\/3305160.3305182"},{"key":"11_CR34","unstructured":"Mitchell, T. M., et al.: Machine learning (1997)"},{"key":"11_CR35","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)"},{"key":"11_CR36","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"issue":"7540","key":"11_CR37","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 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"11_CR38","unstructured":"Newzoo: Global games market report (2021)"},{"key":"11_CR39","unstructured":"Nichol, A., Pfau, V., Hesse, C., Klimov, O., Schulman J.: Gotta learn fast: a new benchmark for generalization in RL. arXiv preprint arXiv:1804.03720 (2018)"},{"key":"11_CR40","doi-asserted-by":"publisher","unstructured":"Now\u00e9, A., Vrancx, P., De Hauwere, Y. M.: Game theory and multi-agent reinforcement learning. In: Wiering, M., van Otterlo, M. (eds) Reinforcement Learning, pp. 441\u2013470. Springer, Berlin (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3_14","DOI":"10.1007\/978-3-642-27645-3_14"},{"key":"11_CR41","unstructured":"O\u2019Donoghue, B., Munos, R., Kavukcuoglu, K., Mnih, V.: Combining policy gradient and Q-learning. arXiv preprint arXiv:1611.01626 (2016)"},{"key":"11_CR42","doi-asserted-by":"crossref","unstructured":"Palma-Ruiz, J. M., Torres-Toukoumidis, A., Gonz\u00e1lez-Moreno, S. E., Valles-Baca, H. G.: An overview of the gaming industry across nations: using analytics with power bi to forecast and identify key influencers, p. e08959. Heliyon (2022)","DOI":"10.1016\/j.heliyon.2022.e08959"},{"key":"11_CR43","unstructured":"Ray, A., Achiam, J., Amodei, D.: Benchmarking safe exploration in deep reinforcement learning, p. 7. arXiv preprint arXiv:1910.01708 (2019)"},{"issue":"19","key":"11_CR44","doi-asserted-by":"publisher","first-page":"10890","DOI":"10.3390\/su131910890","volume":"13","author":"JM Saiz-Alvarez","year":"2021","unstructured":"Saiz-Alvarez, J.M., Palma-Ruiz, J.M., Valles-Baca, H.G., Fierro-Ram\u00edrez, L.A.: Knowledge management in the esports industry: sustainability, continuity, and achievement of competitive results. Sustainability 13(19), 10890 (2021)","journal-title":"Sustainability"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Samara, F., Ondieki, S., Hossain, A. M., Mekni, M.: Online social network interactions (OSNI): a novel online reputation management solution. In: 2021 International Conference on Engineering and Emerging Technologies (ICEET), pp. 1\u20136. IEEE (2021)","DOI":"10.1109\/ICEET53442.2021.9659615"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Scholz, T. M., Scholz, T. M., Barlow: eSports is Business. Springer (2019)","DOI":"10.1007\/978-3-030-11199-1"},{"issue":"7839","key":"11_CR47","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020)","journal-title":"Nature"},{"key":"11_CR48","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.:. Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR (2015)"},{"key":"11_CR49","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"11_CR50","unstructured":"Shabbir, J., Anwer, T.: Artificial intelligence and its role in near future (2018)"},{"key":"11_CR51","unstructured":"Shao, K., Tang, Z., Zhu, Y., Li, N., Zhao, D.: A survey of deep reinforcement learning in video games. arXiv preprint arXiv:1912.10944 (2019)"},{"issue":"7587","key":"11_CR52","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"issue":"6419","key":"11_CR53","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362(6419), 1140\u20131144 (2018)","journal-title":"Science"},{"issue":"7676","key":"11_CR54","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"key":"11_CR55","unstructured":"Silver, T., Chitnis, R.:. PDDLGym: Gym environments from PDDL problems. arXiv preprint arXiv:2002.06432 (2020)"},{"issue":"1","key":"11_CR56","first-page":"24","volume":"8","author":"P Sweetser","year":"2002","unstructured":"Sweetser, P., Wiles, J.: Current AI in games: a review. Australian J. Intell. Info. Proc. Syst. 8(1), 24\u201342 (2002)","journal-title":"Australian J. Intell. Info. Proc. Syst."},{"key":"11_CR57","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-981-16-5559-3_7","volume-title":"Advances on Smart and Soft Computing","author":"Y Tazouti","year":"2022","unstructured":"Tazouti, Y., Boulaknadel, S., Fakhri, Y.: Design and implementation of ImALeG serious game: behavior of non-playable characters (NPC). In: Saeed, F., Al-Hadhrami, T., Mohammed, E., Al-Sarem, M. (eds.) Advances on Smart and Soft Computing. AISC, vol. 1399, pp. 69\u201377. Springer, Singapore (2022). https:\/\/doi.org\/10.1007\/978-981-16-5559-3_7"},{"key":"11_CR58","unstructured":"Terry, J., et al. Pettingzoo: Gym for multi-agent reinforcement learning. Adv. Neural Inf. Proc. Syst. 34 (2021)"},{"key":"11_CR59","unstructured":"Tucker, A., Gleave, A., Russell, S.: Inverse reinforcement learning for video games. arXiv preprint arXiv:1810.10593 (2018)"},{"key":"11_CR60","unstructured":"Wang, Z., et al.: Sample efficient actor-critic with experience replay. arXiv preprint arXiv:1611.01224 (2016)"},{"key":"11_CR61","unstructured":"Wu, Y., Mansimov, E., Grosse, R. B., Liao, S., Ba, J.: Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation. Adv. Neural Inf. Proc. Syst. 30 (2017)"},{"key":"11_CR62","doi-asserted-by":"crossref","unstructured":"Yannakakis, G. N.: Game AI revisited. In: Proceedings of the 9th Conference on Computing Frontiers, pp. 285\u2013292 (2012)","DOI":"10.1145\/2212908.2212954"},{"issue":"4","key":"11_CR63","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1109\/TCIAIG.2014.2339221","volume":"7","author":"GN Yannakakis","year":"2014","unstructured":"Yannakakis, G.N., Togelius, J.: A panorama of artificial and computational intelligence in games. IEEE Trans. Comput. Intell. AI in Games 7(4), 317\u2013335 (2014)","journal-title":"IEEE Trans. Comput. Intell. AI in Games"},{"issue":"03","key":"11_CR64","doi-asserted-by":"publisher","first-page":"322","DOI":"10.26740\/jinacs.v3n03.p322-333","volume":"3","author":"DN Yohanes","year":"2022","unstructured":"Yohanes, D.N., Rochmawati, N.: Implementasi algoritma collision detection dan a*(a star) pada non player character game world of new normal. J. Inf. Comput. Sci. (JINACS) 3(03), 322\u2013333 (2022)","journal-title":"J. Inf. Comput. Sci. (JINACS)"}],"container-title":["Lecture Notes in Networks and Systems","Proceedings of the Future Technologies Conference (FTC) 2022, Volume 1"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18461-1_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,7]],"date-time":"2023-03-07T23:47:14Z","timestamp":1678232834000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18461-1_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,13]]},"ISBN":["9783031184604","9783031184611"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18461-1_11","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"value":"2367-3370","type":"print"},{"value":"2367-3389","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,13]]},"assertion":[{"value":"13 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FTC 2022","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Proceedings of the Future Technologies Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ftc2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/saiconference.com\/FTC","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}