“Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments”, Yi Sun, Faustino Gomez, Juergen Schmidhuber2011-03-29 (RL exploration, Bayes)⁠:

To maximize its success, an AGI typically needs to explore its initially unknown world. Is there an optimal way of doing so?

Here we derive an affirmative answer for a broad class of environments.