What should I do when it is almost impossible to enumerate all possible discrete action spaces in rlFiniteSetSpec ？

Here is the example in the help file:

“如果您的强化学习代理的演员有多个输出，每个输出都有一个离散的动作空间，则可以使用一个可能的离散操作组合来使用 rlFiniteSetSpec 目的。

Suppose that the valid values for a two-output system are [1 2] for the first output and [10 20 30] for the second output. Create a discrete action space specification for all possible input combinations.

actionSpec = rlFiniteSetSpec({[1 10],[1 20],[1 30], ...

[2 10]，[2 20]，[2 30]}）

So actually, I need to list all 3^2000 situations, memory can’t fit at all and it’s almost impossible to train.

So this means that the current MATLAB reinforcement learning framework can't handle this problem?