Long-Term and Short-Term Opponent Intention Inference for Football Multiplayer Policy Learning

Shijie Wang, Zhiqiang Pu, Yi Pan, Boyin Liu, Hao Ma, Jianqiang Yi

Abstract: A highly competitive and confrontational football match is full of strategic and tactical challenges. Therefore, player's cognition on their opponents’ strategies and tactics is quite crucial. However, the match's complexity results in that the opponents’ intentions are often changeable. Under these circumstances, how to discriminate and predict the opponents’ intentions of future actions and tactics is an important problem for football players’ decision-making. Considering that the opponents’ cognitive processes involve deliberative and reactive processes, a long-term and short-term opponent intention inference (LS-OII) method for football multiplayer policy learning is proposed. First, to capture the cognition about opponents’ deliberative process, we design an opponent tactics deduction module for inferring the opponents’ long-term tactical intentions from a macro perspective. Furthermore, an opponent decision prediction module is designed to infer the opponents’ short-term decision which often yields rapid and direct impacts on football matches. Additionally, an opponent-driven incentive module is designed to enhance the players’ causal awareness of the opponents’ intentions, further to improve the players exploration capabilities and effectively obtain outstanding policies. Representative results demonstrate that the LS-OII method significantly enhances the efficacy of players’ strategies in the Google Research Football environment, thereby affirming the superiority of our method.

External IDs:doi:10.1109/tcds.2024.3404061