Abstract
Designers often improve the performance of artificial agents by specializing them. We can make a rough, but useful distinction between specialization to a task and specialization to an environment. Specialization to an environment can be difficult to understand: it may be unclear on what properties of the environment the agent depends, or in what manner it depends on each individual property. In this paper, I discuss a method for analyzing specialization into a series of conditional optimizations: formal transformations which, given some constraint on the environment, map mechanisms to more efficient mechanisms with equivalent behavior. I apply the technique to the analysis of the vision and control systems of a working robot system in day to day use in our laboratory. The method is not intended as a general theory for automated synthesis of arbitrary specialized agents. Nonetheless, it can be used to perform post-hoc analysis of agents so as to make explicit the environment properties required by the agent and the computational value of each property. This post-hoc analysis helps explain performance in normal environments and predict performance in novel environments. In addition, the transformations brought out in the analysis of one system can be reused in the synthesis of future systems.
Original language | English (US) |
---|---|
Pages (from-to) | 1-30 |
Number of pages | 30 |
Journal | Artificial Intelligence |
Volume | 73 |
Issue number | 1-2 |
DOIs | |
State | Published - Feb 1995 |
Funding
Phil Agre, Rod Brooks, Bruce Donald, Eric Grimson, Maja Mataric, David Michael, Ray Paton, Stan Rosenschein, and Lynn Stein all provided much needed feedback during the developmento f these ideas. The reviewersp rovided many useful suggestions for improving the presentation.S upport for this researchw as provided in part by the University Research Initiative under Office of Naval Research contract NOOO14-86-K-0685, and in part by the Advanced Research Projects Agency under Office of Naval Research contract N00014-85-K-0124.
ASJC Scopus subject areas
- Language and Linguistics
- Linguistics and Language
- Artificial Intelligence