Inverse Reinforcement Learning on Humans in Their Best State

What if we did this inverse reinforcement learning on humans in their best state so now you're trying to learn the preferences of say people after they are extremely comfortable and they are thinking about what the optimal future for everyone on earth could be. Could we train Alex on a select group of people who represent the best of humanity? So again I think that this option isn't something new added by inverse reinforcement learning we could do regular reinforcement learning with a select best group of people but in either case the answer is just going to be kind of like the select best groupof people are going to have some quirks or mistakes they make.