Computational-level Analysis of Constraint Compliance for General Intelligence
This addresses the challenge of making AI agents behave predictably and reliably in complex human-like environments, but it is incremental as it focuses on analysis and an exploratory implementation without proven results.
The paper tackles the problem of enabling general AI agents to handle messy real-world constraints like rules and norms, and proposes a computational-level analysis to characterize complexity and outline an initial implementation approach.
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.