LSAFJiu: A Low-Resource Algorithm for Tibetan Jiu Chess Based on Long Sequence Action Forecasting

Tibetan Jiu Chess, the national intangible cultural heritage of China, involves complex gameplay with both layout and battle stages, presenting a vast action space. Deep learning effectiveness is often limited by computational and data constraints. To address this, we propose LSAFJiu, a low-resource algorithm based on long sequence action forecasting (LSAF). Its innovation combines an LSAF model, a policy network, and a value network to evaluate game tree leaf nodes. The LSAF model incorporates the ActionFormer for the layout stage and an action-state autoencoding planner for the battle stage, aimed at enhancing decision-making capabilities while reducing resource consumption. The policy and value networks are built on the ResNet50 architecture, utilizing a serial stacked activation function to minimize hardware requirements and improve prediction accuracy. To train the initial policy network, 20000 high-quality game instances were generated by three intelligent programs grounded in human expertise, effectively reducing self-play training time. Experiments conducted on two 2060 GPUs demonstrated that LSAFJiu increased the winning rate by 30.5% while requiring only 2.51% of the simulation time needed by the policy network alone. Additionally, the serial stacked activation function improved prediction accuracy by at least 2%. The overall winning rate of LSAFJiu reached 88% within a reasonable decision time. LSAFJiu is an efficient, low-resource algorithm that offers accurate decision-making for Tibetan Jiu Chess.