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 106
- Downloads 0
Unmanned Ground Vehicle with Stereoscopic Vision for a Safe Autonomous Exploration
At present there are several systems in cars that provide assistance to the driver and the tendency is that these systems are increasingly efficient and that for their operation do not require the intervention of the dri...
Towards Improving the Quality of Present MAC Protocols for LECIM Systems
Wireless networking system is quickly growing in the field of communication technology due to its usefulness and huge applications. To make the system more effective to the users its lower energy consumption, security, r...
Hybrid Forecasting Scheme for Financial Time-Series Data using Neural Network and Statistical Methods
Currently, predicting time series utilizes as interesting research area for temporal mining aspects. Financial Time Series (FTS) delineated as one of the most challenging tasks, due to data characteristics is devoid of l...
Unifying Modeling Language-Merise Integration Approach for Software Design
Software design is the most crucial step in the software development process that is why it must be given a good care. Software designers must go through many modeling steps to end up with a good design that will allow f...
Robot Arm Analysis based on Master Device Pneumatic Actuators
Advances in technology have expanded the use of soft actuators in various fields especially in robotics, rehabilitation and medical field. Soft actuator development provides many advantages, primarily being simple struct...