Meta-Reasoning Architecture Methodological Assumptions

Four key assumptions drove the design of the Meta-Reasoning Architecture or MAX:
  1. Autonomous robots must mix reaction with planning;
  2. Limits on computational resources requires that learning be directed by goals;
  3. Integration of capabilities should give priority to reaction, i.e., the agent must be situation-directed; and
  4. Open, homogeneous, declarative knowledge, separate control rules and explicitly specified reasoning and learning operators can facilitate the requisite capabilities.


Go to General Discussion of Methodological Assumptions
Return to the top of this architecture.

Go to NEXT page.