Research Repository

Knowledge-based fast evolutionary MCTS for general video game playing

Perez, D and Samothrakis, S and Lucas, S (2014) Knowledge-based fast evolutionary MCTS for general video game playing. In: UNSPECIFIED, ? - ?.


Download (526kB) | Preview


© 2014 IEEE. General Video Game Playing is a game AI domain in which the usage of game-dependent domain knowledge is very limited or even non existent. This imposes obvious difficulties when seeking to create agents able to play sets of different games. Taken more broadly, this issue can be used as an introduction to the field of General Artificial Intelligence. This paper explores the performance of a vanilla Monte Carlo Tree Search algorithm, and analyzes the main difficulties encountered when tackling this kind of scenarios. Modifications are proposed to overcome these issues, strengthening the algorithm's ability to gather and discover knowledge, and taking advantage of past experiences. Results show that the performance of the algorithm is significantly improved, although there remain unresolved problems that require further research. The framework employed in this research is publicly available and will be used in the General Video Game Playing competition at the IEEE Conference on Computational Intelligence and Games in 2014.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: IEEE Conference on Computatonal Intelligence and Games, CIG
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Jim Jamieson
Date Deposited: 04 Dec 2014 13:41
Last Modified: 30 Jan 2019 16:18

Actions (login required)

View Item View Item