I would like to use reinforcement learning for the optimisation of a given function under some contraints.

Take for example the following problems:

min f(x, y, z) with respect to x, y, z such that x, y and belong to a given domain

Having some basic knowledge about RL, I assume that the framework could be adapted to handle this problem but I am unable to state it correctly from a RL point of view.

My second question is how efficient RL in these topics? If there any useful resources, I will be thankful.



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.