General and Reusable Indexical Policies and Sketches
Abstract: Recently, a simple but powerful language for expressing and learning general policies and problem decompositions (sketches) has been introduced, which is based on collections of rules defined on a set of Boolean and numerical features. In this work, we consider extensions of this basic language aimed at making policies and sketches more flexible and reusable. For this, three basic extensions are considered: 1) internal memory states, as in finite state controllers, 2) indexical features, whose values are a function of the state and a number of internal registers that can be loaded with objects, and 3) modules that wrap up policies and sketches and allow them to call each other by passing parameters. In addition, unlike previously defined policies that select actions indirectly by the selection of state transitions, the new language allows for the selection of actions directly. The expressive power of the resulting language for recombining policies and sketches is illustrated through examples. The problem of learning policies and sketches in the new language is left for future work.
Submission Number: 86
Loading