How many rewards schemes are there in reinforcement learning?

Question

I am new to the reinforcement learning, in the textbook there is a question I am confused. It says to think about three substantially different reward schemes for a given policy on the grid world, and for each scheme I should give rewards and discount.

I can think of one, but it needs three substantially different. What could others look like?

Picture:

Answer 1

The reward scheme determines what your agent is to be learning. There is no limit.