I can't seem to understand the difference between q-learning and utility learning clearly, I know that q learning means learning the utility of actions available to a state rather than learning the utility of each state(util learning). But when it com...

If we tried making an implementation for our agent with an algorithm we know is superior but we fail to do so and go back to a more naive but working algorithm, how will we explain this in our report. My question is how will I convince that my strateg...