This paper addresses the following question: how should we update our beliefs after observing some incomplete data, in order to make credible predictions about new, and possibly i...
A simple learning rule is derived, the VAPS algorithm, which can be instantiated to generate a wide range of new reinforcementlearning algorithms. These algorithms solve a number ...
We present a general, consistency-based framework for belief change. Informally, in revising K by , we begin with and incorporate as much of K as consistently possible. Formally, ...
We consider non-Horn Deductive Data Bases (DDB) represented in a First Order language without function symbols. In this context the DDB is an incomplete description of the world. ...
Proper scoring rules, particularly when used as the basis for a prediction market, are powerful tools for eliciting and aggregating beliefs about events such as the likely outcome...