Consistency of Feature Markov Processes [chapter]

Peter Sunehag, Marcus Hutter
2010 Lecture Notes in Computer Science  
We are studying long term sequence prediction (forecasting). We approach this by investigating criteria for choosing a compact useful state representation. The state is supposed to summarize useful information from the history. We want a method that is asymptotically consistent in the sense it will provably eventually only choose between alternatives that satisfy an optimality property related to the used criterion. We extend our work to the case where there is side information that one can
more » ... advantage of and, furthermore, we briefly discuss the active setting where an agent takes actions to achieve desirable outcomes.
doi:10.1007/978-3-642-16108-7_29 fatcat:eydla6o4f5gdhhhs4xhrcu7cfu