On Policy Reuse: An Expressive Language for Representing and Executing General Policies that Call Other Policies
This work addresses the need for more reusable and expressive policy representations in AI planning, but it appears incremental as it builds directly on prior language extensions.
The authors tackled the problem of making general policies and problem decompositions more flexible and reusable by extending an existing language with internal memory states, indexical features, and modules for policy calls. They demonstrated the expressive power of the resulting language through examples, but did not report concrete numerical results.
Recently, a simple but powerful language for expressing and learning general policies and problem decompositions (sketches) has been introduced in terms of rules defined over a set of Boolean and numerical features. In this work, we consider three extensions of this language aimed at making policies and sketches more flexible and reusable: internal memory states, as in finite state controllers; indexical features, whose values are a function of the state and a number of internal registers that can be loaded with objects; and modules that wrap up policies and sketches and allow them to call each other by passing parameters. In addition, unlike general policies that select state transitions rather than ground actions, the new language allows for the selection of such actions. The expressive power of the resulting language for policies and sketches is illustrated through a number of examples.