Efficiently Mastering the Game of NoGo with Deep Reinforcement Learning Supported by Domain Knowledge

Computer games have been regarded as an important field of artificial intelligence (AI) for a long time. The AlphaZero structure has been successful in the game of Go, beating the top professional human players and becoming the baseline method in computer games. However, the AlphaZero training process requires tremendous computing resources, imposing additional difficulties for the AlphaZero-based AI. In this paper, we propose NoGoZero+ to improve the AlphaZero process and apply it to a game similar to Go, NoGo. NoGoZero+ employs several innovative features to improve training speed and performance, and most improvement strategies can be transferred to other nonspecific areas. This paper compares it with the original AlphaZero process, and results show that NoGoZero+ increases the training speed to about six times that of the original AlphaZero process. Moreover, in the experiment, our agent beat the original AlphaZero agent with a score of 81:19 after only being trained by 20,000 self-play games’ data (small in quantity compared with 120,000 self-play games’ data consumed by the original AlphaZero). The NoGo game program based on NoGoZero+ was the runner-up in the 2020 China Computer Game Championship (CCGC) with limited resources, defeating many AlphaZero-based programs. Our code, pretrained models, and self-play datasets are publicly available. The ultimate goal of this paper is to provide exploratory insights and mature auxiliary tools to enable AI researchers and computer-game communities to study, test, and improve these promising state-of-the-art methods at a much lower cost of computing resources.