局部可观测环境下未来信息辅助的无模型深度强化学习

常芳芳, 陈祺航, 刘云龙

Model⁃free deep reinforcement learning with future information in partially observable domains

Fangfang Chang, Qihang Chen, Yunlong Liu

图5 Regular任务下的训练得分曲线

Fig.5 Performance in Regular task