so in an unknown environment, which one should be used? Q-learning can just learn state-action pairs, but utility learning can just learn the transition model then use it to calculate state utilities. I'm having difficulty finding pros and cons of usi...

When our agents are being assessed, for single game will the max amount of players always be 10 as specified by the game rules?

Hey, if we wanted to try to make some kind of learning agent are we allowed to use the run game run tournament code. I intuitively want to think we can, but just wanted to make sure.

Just wanted to ask, in reference to project how many more lectures until we have enough knowledge to sufficiently compare the techniques that can be used? or are we supposed to research techniques? or are we good to start now? I feel we've literal...