GAIG Game AI Research Group @ QMUL

Deep Reinforcement Learning for General Video Game AI

2018
Torrado, Ruben Rodriguez and Bontrager, Philip and Togelius, Julian and Liu, Jialin and Perez-Liebana, Diego

Abstract

The General Video Game AI (GVGAI) competition and its associated software framework provides a way of benchmarking AI algorithms on a large number of games written in a domain-specific description language. While the competition has seen plenty of interest, it has so far focused on online planning, providing a forward model that allows the use of algorithms such as Monte Carlo Tree Search. In this paper, we describe how we interface GVGAI to the OpenAI Gym environment, a widely used way of connecting agents to reinforcement learning problems. Using this interface, we characterize how widely used implementations of several deep reinforcement learning algorithms fare on a number of GVGAI games. We further analyze the results to provide a first indication of the relative difficulty of these games relative to each other, and relative to those in the Arcade Learning Environment under similar conditions.

Cite this work

@inproceedings{torrado2018deep,
author= {Torrado, Ruben Rodriguez and Bontrager, Philip and Togelius, Julian and Liu, Jialin and Perez-Liebana, Diego},
title= {{Deep Reinforcement Learning for General Video Game AI}},
year= {2018},
booktitle= {{Proc. of the IEEE Conference on Computational Intelligence and Games (CIG)}},
month= {Aug},
pages= {1--8},
abstract= {The General Video Game AI (GVGAI) competition and its associated software framework provides a way of benchmarking AI algorithms on a large number of games written in a domain-specific description language. While the competition has seen plenty of interest, it has so far focused on online planning, providing a forward model that allows the use of algorithms such as Monte Carlo Tree Search. In this paper, we describe how we interface GVGAI to the OpenAI Gym environment, a widely used way of connecting agents to reinforcement learning problems. Using this interface, we characterize how widely used implementations of several deep reinforcement learning algorithms fare on a number of GVGAI games. We further analyze the results to provide a first indication of the relative difficulty of these games relative to each other, and relative to those in the Arcade Learning Environment under similar conditions.},
}

Similar Posts

Comments