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 103
- Downloads 0
Micro Agent and Neural Network based Model for Data Error Detection in a Real Time Data Stream
In this paper, we present a model for learning and detecting the presence of data type errors in a real time big data stream processing context. The proposed approach is based on a collection of micro-agents. Each micro-...
Image Transmission Model with Quality of Service and Energy Economy in Wireless Multimedia Sensor Network
The objective of this article is to present the efficiency of image compression in the Wireless Multimedia Sensor Network (WMSN), the method used in this work is based on the lifting scheme coupled with the SPIHT coding...
On Prospects of Development of Telecommunication Systems and Services based on Virtual Reality Technology
Virtual reality technologies are considered to be a basis and a promising development trend of telecommunication systems’ and services. New opportunities and sci-tech problems that need to be solved are currently undergo...
Middleware to integrate heterogeneous Learning Management Systems and initial results
The use of the Learning Management Systems (LMS) has been increased. It is desirable to access multiple learning objects that are managed by Learning Management Systems. The diversity of LMS allow us to consider them as...
Detecting Distributed Denial of Service Attacks Using Data Mining Techniques
Users and organizations find it continuously challenging to deal with distributed denial of service (DDoS) attacks. . The security engineer works to keep a service available at all times by dealing with intruder attacks....