本文讨论了平均逼近，给出了四个定理，是对存在定理、特征定理，唯一性定理的补充。

This paper discusses average approximation and proposes four theorems which are the supplement for existence theorem, characteristic theorem and solitariness theorem.

youdao

文中基于性能势理论，证明了平均奖赏强化学习的逼近定理。

In this paper, the approximate theorem of average reward reinforcement learning is proven by means of the theory of performance potentials.

youdao