Hey, I have a roguelike deckbuilding game I want to train an agent to play using pure unsupervised RL; I chose PPO as I understand (to my amateur knowledge) that is the most fitting algorithm. I have a very large categorical space that I have to send i…

First, I hope this isn't against the sub rules; I looked over them and couldn't find anything that strictly forbids looking for paid experts. That being said, I'm looking for experts with proven experience in the RL field for a few hours of…