Write me a Q learning Algorithm in Reinforcement Learning

Hello,

I have a scenario where I need to be able to change the position of the mobile app icons according to their usage.

The algorithm I need to use is Q learning for this. The inputs I have decided on are the id of the app, position of the app, the usage of the app. Periodically these data will be sent from the phone to the algorithm. The actions I expect is after considering the usage time the position of the app should be changed. The rewards should be based on whether the user has changed any positions of the apps after the position changes done by the mobile phone operating system from the output given by the algorithm.

I am capable of providing the inputs and changing the positions of the apps programmatically, but I have been stuck writing the algorithm, coming up with all the required inputs and the output as well.

I will be able to provide further details as well , this is just an overview.

Will you be able to support in writing the algorithm?
If so please also let me know if there is any custom price you would like

Thank you