Training an Agent for FPS Doom Game using Visual Reinforcement Learning and VizDoom

Abstract

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 testbeds 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 semirealistic 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.

Computer-Aided Diagnostic System for Early Detection of Acute Renal Transplant Rejection Using Diffusion-Weighted MRI

“…Likewise, DL-based methods are unlikely to replace human experts any time soon. The performance of DL has equaled or surpassed human performance for some nonmedical tasks such as playing computer games 385 and, as illustrated by the many cited publications in this paper, DL has also been quite successful in a variety of medical imaging applications. However, most medical imaging tasks are far from solved 386 and the optimal DL method and architecture for each individual task and application area have not yet been established.…”

Deep learning in medical imaging and radiation therapy

“…Likewise, DL‐based methods are unlikely to replace human experts any time soon. The performance of DL has equaled or surpassed human performance for some nonmedical tasks such as playing computer games and, as illustrated by the many cited publications in this paper, DL has also been quite successful in a variety of medical imaging applications. However, most medical imaging tasks are far from solved and the optimal DL method and architecture for each individual task and application area have not yet been established.…”

Optimal Skipping Rates: Training Agents with Fine-Grained Control Using Deep Reinforcement Learning

“…Each convolutional layer is trailed by a maxpooling layer with max pooling of size 2 and ReLU function for activation. Moreover, there is a fully connected layer with 800 leaky rectified linear units and an output layer with 8 linear units corresponding to the 8 combinations of the 3 available actions, i.e., left, right, and shooting [12].…”

“…It is primarily intended for research in machine visual learning, and in particular for deep reinforcement learning. One of the recent research works based on visual reinforcement learning and the ViZ-Doom AI research platform is proposed in [12] by training an AI agent for the game Doom. The agent outperformed both human players and inbuilt game agents.…”