about the observation

[sunnyswag]

It seems that you use activity index as the obervation code, I think there are other imformation we need to feed to the agent. That will get a better result.
The amount of information is too little, simple Q learning feels like enough.

[H2SO4T]

Hi @sunnyswag, yes, I use the activity index and also the widgets that are currently on the screen. However, if you think there are other optimizations to be made, I encourage you to do so. Unfortunately, I have very little time to dedicate to ARES in these months.