In general, there are two types of transition functions in reinforcement learning. Mathematically, they are as follows
#1: Stochastic state transition function:
$$T : S \times A \times S \rightarrow [0, 1]$$
#2: Deterministic state transition function:
$$T : S \times A \rightarrow S$$
Is it possible to make the transition function change as the game progress? Or is it impossible to assume such a transition function as it cannot qualify to be a function?
Or in other words, I may want to introduce something as follows:
#3: Dynamic state transition function:
$$T : S \times A \times X \rightarrow S$$
where $X$ is some continuous set.