Training an Agent for FPS Doom Game using Visual Reinforcement Learning and VizDoom
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 12
Abstract
Because of the recent success and advancements in deep mind technologies, it is now used to train agents using deep learning for first-person shooter games that are often outperforming human players by means of only screen raw pixels to create their decisions. A visual Doom AI Competition is organized each year on two different tracks: limited death-match on a known map and a full death-match on an unknown map for evaluating AI agents, because computer games are the best test-beds for testing and evaluating different AI techniques and approaches. The competition is ranked based on the number of frags each agent achieves. In this paper, training a competitive agent for playing Doom’s (FPS Game) basic scenario(s) in a semi-realistic 3D world ‘VizDoom’ using the combination of convolutional Deep learning and Q-learning by considering only the screen raw pixels in order to exhibit agent’s usefulness in Doom is proposed. Experimental results show that the trained agent outperforms average human player and inbuilt game agents in basic scenario(s) where only move left, right and shoot actions are allowed.
Authors and Affiliations
Khan Adil, Feng Jiang, Shaohui Liu, Aleksei Grigorev, B. B. Gupta, Seungmin Rho
Keywords
Related Articles
- EP ID EP251587
- DOI 10.14569/IJACSA.2017.081205
- Views 61
- Downloads 0
Identifying and Prioritizing Evaluation Criteria for User-Centric Digital Identity Management Systems
Identity Management systems are used for securing digital identity of users in reliable, automated and compatible way. Service providers employ identity management systems which are cost effective and scalable but cause...
framework for Marketing Libraries in the Post-Liberalized Information and Communications Technology Era
The role of library is professional and is fast customizing to altering technological platforms. Our subscriber’s perceptions of the nature of our libraries are also altering like never before – particularly...
A Study of MCA Learning Algorithm for Incident Signals Estimation
Many signal subspace-based approaches have already been proposed for determining the fixed Direction of Arrival (DOA) of plane waves impinging on an array of sensors. Two procedures for DOA estimation based neural networ...
A New Threshold Based Penalty Function Embedded MOEA/D
Recently, we proposed a new threshold based penalty function. The threshold dynamically controls the penalty to infeasible solutions. This paper implants the two different forms of the proposed penalty function in the mu...
Big Data Classification Using the SVM Classifiers with the Modified Particle Swarm Optimization and the SVM Ensembles
The problem with development of the support vector machine (SVM) classifiers using modified particle swarm optimization (PSO) algorithm and their ensembles has been considered. Solving this problem would allow fulfilling...