In ergodic MDPs we consider stationary distributions of policies that coincide in all but n states, in which one of two possible actions is chosen. We give conditions and formulas...
Many formal models of cognition implicitly use subjective probability distributions to capture the assumptions of human learners. Most applications of these models determine these...
We consider the equivalence problem for labeled Markov chains (LMCs), where each state is labeled with an observation. Two LMCs are equivalent if every finite sequence of observat...
Laurent Doyen, Thomas A. Henzinger, Jean-Fran&cced...
Abstract. This paper proposes an entropy based Markov chain (EMC) fusion technique and demonstrates its applications in multisensor fusion. Self-entropy and conditional entropy, wh...
We study a time series model that can be viewed as a decision tree with Markov temporal structure. The model is intractable for exact calculations, thus we utilize variational app...
Michael I. Jordan, Zoubin Ghahramani, Lawrence K. ...