基于深度强化学习的对手建模方法研究综述

徐浩添, 秦龙, 曾俊杰, 胡越, 张琪

Research Progress of Opponent Modeling Based on Deep Reinforcement Learning

Haotian Xu, Long Qin, Junjie Zeng, Yue Hu, Qi Zhang

图4 递归推理过程概率图模型

Fig. 4 Probabilistic graph model of recursive inference process