Correlated Action Effects in Decision Theoretic Regression

Papers

Much recent research in decision theoretic planning has adopted Markov decision processes as the model of choice, and has attempted to make their solution more tractable by exploiting problem structure: Structured policy construction algorithms achieve this by a decision theoretic analogue of goal regression, using action descriptions based on Bayesian networks with treestructured conditional probability tables. At present, these algorithms are unable to deal with actions with correlated effects. We describe a new decision theoretic regression operator that corrects this weakness.