Computational-level Analysis of Constraint Compliance for General Intelligence
Abstract
Human behavior is conditioned by codes and norms that constrain action. Rules, ``manners,'' laws, and moral imperatives are examples of classes of constraints that govern human behavior. These systems of constraints are "messy:" individual constraints are often poorly defined, what constraints are relevant in a particular situation may be unknown or ambiguous, constraints interact and conflict with one another, and determining how to act within the bounds of the relevant constraints may be a significant challenge, especially when rapid decisions are needed. Despite such messiness, humans incorporate constraints in their decisions robustly and rapidly. General, artificially-intelligent agents must also be able to navigate the messiness of systems of real-world constraints in order to behave predictability and reliably. In this paper, we characterize sources of complexity in constraint processing for general agents and describe a computational-level analysis for such constraint compliance. We identify key algorithmic requirements based on the computational-level analysis and outline an initial, exploratory implementation of a general approach to constraint compliance.
- Publication:
-
arXiv e-prints
- Pub Date:
- March 2023
- DOI:
- 10.48550/arXiv.2303.04352
- arXiv:
- arXiv:2303.04352
- Bibcode:
- 2023arXiv230304352W
- Keywords:
-
- Computer Science - Artificial Intelligence;
- I.2.0;
- I.2.8
- E-Print:
- 10 pages, 2 figures. Accepted for presentation at AGI 2023. Corrected author list (segmented list) and abstract text artifacts