Consistency of Feature Markov Processes

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 take advantage of and, furthermore, we briefly discuss the active setting where an agent takes actions to achieve desirable outcomes. Contents

• Type: Conference
• Year: 2010
• Where: ALT
• Authors: Peter Sunehag, Marcus Hutter
• Keywords: Agent Takes Actions, ALT 2010, Compact Useful State, Machine Learning, Term Sequence Prediction