Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments [chapter]

Yi Sun, Faustino Gomez, Jürgen Schmidhuber
2011 Lecture Notes in Computer Science  
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.
doi:10.1007/978-3-642-22887-2_5 fatcat:46vubkys7jetnmwxkd66n3u6sq