metagoal
Metagoals Endowing Self-Modifying AGI Systems with Goal Stability or Moderated Goal Evolution: Toward a Formally Sound and Practical Approach
We articulate here a series of specific metagoals designed to address the challenge of creating AGI systems that possess the ability to flexibly self-modify yet also have the propensity to maintain key invariant properties of their goal systems 1) a series of goal-stability metagoals aimed to guide a system to a condition in which goal-stability is compatible with reasonably flexible self-modification 2) a series of moderated-goal-evolution metagoals aimed to guide a system to a condition in which control of the pace of goal evolution is compatible with reasonably flexible self-modification The formulation of the metagoals is founded on fixed-point theorems from functional analysis, e.g. the Contraction Mapping Theorem and constructive approximations to Schauder's Theorem, applied to probabilistic models of system behavior We present an argument that the balancing of self-modification with maintenance of goal invariants will often have other interesting cognitive side-effects such as a high degree of self understanding Finally we argue for the practical value of a hybrid metagoal combining moderated-goal-evolution with pursuit of goal-stability -- along with potentially other metagoals relating to goal-satisfaction, survival and ongoing development -- in a flexible fashion depending on the situation
Report 83 45 A Framework for Circuit Design . S Stanford Christopher Tong Dec 1983
The process of circuit design is complex largely because the required knowledge takes many forms. We present a framework that contains such design descriptions as components, plans, goals, and tradeoffs. The design process is represented by tasks, which synthesize and revise descriptions, and principles that should be upheld by descriptions. Con, -)1 of the circuit design process involves sequencing the creation and execution of tasks and the.naimainence of principles. Control is knowledge-intensive: different design processes are represented by such control descriptions as strategies and metagoals. We provide examples of design tasks, principles, and control descriptions. Finally, we describe a computer program based on this framework.