ICGA Journal - Volume 46, issue 2

Authors: Winands, Mark

Article Type: Editorial

DOI: 10.3233/ICG-240257

Citation: ICGA Journal, vol. 46, no. 2, pp. 39-39, 2024

Authors: Demura, Yosuke | Kaneko, Tomoyuki

Article Type: Research Article

Abstract: AlphaZero has achieved superhuman performance in Go, chess, and shogi with a general reinforcement learning (RL) algorithm. This achievement is remarkable because AlphaZero does not rely on any training dataset of strong players. However, AlphaZero-style training requires substantial computational resources. Gumbel AlphaZero, a recently introduced more efficient version of AlphaZero, reduces the computational cost of AlphaZero training. The goal of this study is to further improve the playing strength of Gumbel AlphaZero under a limited amount of computational resources. We focus on the diversity in training games, inspired by procedural generation and domain randomization in RL studies, and propose a …novel method, initial state diversification . This method diversifies the initial states of a self-play game to encourage the RL agent to understand the game in a more general manner through diverse experiences. For example, in shogi, the initial state of each self-play game is diversified by rearranging the pieces under realistic domain constraints. Experiments demonstrated that training with initial state diversification improves the playing strength of Gumbel AlphaZero in shogi, within the same computational budget for training. Show more

Keywords: Reinforcement learning, AlphaZero, Gumbel AlphaZero, shogi, Chess960

DOI: 10.3233/ICG-240255

Citation: ICGA Journal, vol. 46, no. 2, pp. 40-66, 2024

Authors: Björnsson, Yngvi

Article Type: Research Article

Abstract: Chess, once famously referred to as the drosophila of artificial intelligence (AI) research, has been a significant domain for developing intelligent AI agents capable of achieving super-human performance in domains previously dominated by humans. However, the emphasis on unceasingly improved playing strength has come at the cost of neglecting other fundamental aspects of intelligent agents, such as being capable of explaining the rationality behind their decisions in human-understandable terms. The need for such capabilities may be even more profound now than before, partly because such agents may be capable of learning novel concepts of interest to us humans, for …example, as recently demonstrated in the game of chess. In this paper, we survey the state of explainable AI in chess-playing agents, arguing that chess may indeed hold a promise as an admissible domain for explainable AI. Show more

Keywords: Explainable AI, chess, game playing

DOI: 10.3233/ICG-240256

Citation: ICGA Journal, vol. 46, no. 2, pp. 67-75, 2024

Authors: Liu, Jialin | Yannakakis, Georgios N.

Article Type: Research Article

DOI: 10.3233/ICG-240252

Citation: ICGA Journal, vol. 46, no. 2, pp. 76-78, 2024

Authors: Nagels, Leo

Article Type: Obituary

DOI: 10.3233/ICG-240250

Citation: ICGA Journal, vol. 46, no. 2, pp. 79-80, 2024