Introducing interactive help for reinforcement learners

The reinforcement learning problem is a very difficult problem when considering real-size applications. To solve it, we think that many issues should be studied altogether. To achieve such an endeavor, we also think that it is quite common that human begins can provide help on-the-fly to the reinforcement learner, that is when he/she sees how the learner is (mis)behaving, or could perform better than what it is currently performing. This work precisely aims at designing a principled way to help a reinforcement learner in such a context. We put the emphasis on the fact that the help being provided cannot be expected to be perfect (whatever “perfect” might mean here...).