Affiliation:
1. 2AI, School of Technology, Polytechnic Institute of Cávado and Ave, 4750 Barcelos, Portugal
2. LASI—Associate Laboratory of Intelligent Systems, 4800 Guimarães, Portugal
Abstract
Reinforcement Learning is one of the many machine learning paradigms. With no labelled data, it is concerned with balancing the exploration and exploitation of an environment with one or more agents present in it. Recently, many breakthroughs have been made in the creation of these agents for video game machine learning development, especially in first-person shooters with platforms such as ViZDoom, DeepMind Lab, and Unity’s ML-Agents. In this paper, we review the state-of-the-art of creation of Reinforcement Learning agents for use in multiplayer deathmatch first-person shooters. We selected various platforms, frameworks, and training architectures from various papers and examined each of them, analysing their uses. We compared each platform and training architecture, and then concluded whether machine learning agents can now face off against humans and whether they make for better gameplay than traditional Artificial Intelligence. In the end, we thought about future research and what researchers should keep in mind when exploring and testing this area.
Funder
national funds
Norte Portugal Regional Operational Program
Subject
Computational Mathematics,Computational Theory and Mathematics,Numerical Analysis,Theoretical Computer Science
Reference45 articles.
1. Mastering the game of Go with deep neural networks and tree search;Silver;Nature,2016
2. Mastering chess and shogi by self-play with a general reinforcement learning algorithm;Silver;Science,2018
3. Human-level control through deep reinforcement learning;Mnih;Nature,2015
4. Reinforcement Learning in First Person Shooter Games;McPartland;IEEE Trans. Comput. Intell. AI Games,2011
5. ElDahshan, K., Farouk, H., and Mofreh, E. (2022, January 8–9). Deep Reinforcement Learning based Video Games: A Review. Proceedings of the 2022 2nd International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), Cairo, Egypt.
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献