Playing a FPS Doom Video Game with Deep Visual Reinforcement Learning
- Authors: Adil Khan 1,2, Jiang F.1, Liu S.1, Omara I.3
-
Affiliations:
- Harbin Institute of Technology, School of Computer Science and Technology
- Higher Education Department
- Department of Mathematics, Faculty of Science, Menoufia University
- Issue: Vol 53, No 3 (2019)
- Pages: 214-222
- Section: Article
- URL: https://journals.rcsi.science/0146-4116/article/view/175823
- DOI: https://doi.org/10.3103/S0146411619030052
- ID: 175823
Cite item
Abstract
Because of the advancement in Deep visual reinforcement learning, now autonomous game agents are allowed to perform well which often leave behind human beings by using only the raw screen pixels for making their actions or decisions. In this paper, we propose Deep Q-Network (DQN) and a Deep Recurrent Q-Learning Network (DRQN) implementation by playing the Doom video game. Our findings are based on a publication from Lample and Chaplot (2016). Deep Q-learning under two variants (DQN and DRQN) applied is presented first, then how we build an implementation of a testbed for such algorithms is described. we presented our results on a simplified game scenario(s) by showing the predicted enemy positions (game features) with the difference in performance of DQN and DRQN. Finally, unlike other existing works, we show that our proposed architecture performs better with an accuracy of almost 72% in predicting the enemy positions.
About the authors
Adil Khan
Harbin Institute of Technology, School of Computer Science and Technology; Higher Education Department
Author for correspondence.
Email: DrAdil@hit.edu.cn
China, Harbin, Heilongjiang, 150001; KPK
Feng Jiang
Harbin Institute of Technology, School of Computer Science and Technology
Author for correspondence.
Email: fjiang@hit.edu.cn
China, Harbin, Heilongjiang, 150001
Shaohui Liu
Harbin Institute of Technology, School of Computer Science and Technology
Author for correspondence.
Email: shliu@hit.edu.cn
China, Harbin, Heilongjiang, 150001
Ibrahim Omara
Department of Mathematics, Faculty of Science, Menoufia University
Author for correspondence.
Email: I_omara84@hit.edu.cn
Egypt, Al Minufya