Learned models for continuous planning.
Matthew D. Schmill, Tim Oates, Paul R. Cohen · 1999
We are interested in the nature of activity -- structured behavior of nontrivial duration -- in intelligent agents. We believe that the development of activity is a continual process in which simpler activities are composed, via planning, to form more sophisticated ones in a hierarchical fashion. The success or failure of a planner depends on its models of the environment, and its ability to implement its plans in the world. We describe an approach to generating dynamical models of activity from real-world experiences and explain how they can be applied towards planning in a continuous state space. 1 Introduction We are interested in the problem of how activity emerges in an intelligent agent. We believe that activity plays a critical role in the development of many high-level cognitive structures: classes, concepts, and language, to name a few. Thus, it is our goal to derive and implement a theory of the development of activity in intelligent agents and implement it using the Pioneer...