Editorial: New horizons
The last couple of years, we have seen a research shift from developing search techniques such as Monte-Carlo Tree Search towards the use of deep-learning models in games. The first contribution of this issue, Initial state diversification for efficient AlphaZero-style training, by Yosuke Demura and Tomoyuki Kaneko, reflects this shift in focus. The article deals with Gumbel AlphaZero, a more efficient version of AlphaZero, which enables researchers to train agents with relatively few computational resources. The authors discuss how to further improve the playing strength of this engine under a limited amount of computational resources. Another research shift is from developing new AI engines to play games, towards developing methods that actually explain why the engine made a certain move. In the second contribution, Chess and explainable AI, Yngvi Björnsson makes the case that chess should become the drosophila of explainable AI research.
In this issue, there is also a report on the workshop on Computational Intelligence and Games 2024, which was held at the Southern University of Science and Technology (SUSTech), Shenzhen, China. The event demonstrated the various roles of AI in different fields, particularly how AI techniques widely studied in the computer games research community are being leveraged to advance and help other research fields and applications.
This issue ends on a sad note with the obituary of Ton Tillemans, who participated with his Draughts engine TD King in many of our Computer Olympiads and published several tournaments reports in the ICGA journal. Ton will be deeply missed by our community. On behalf of the ICGA, I would like to offer our sincere condolences to his family.
Mark Winands