
TL;DR
This paper develops a theoretical framework for how bounded Bayesian agents manage and revise simplified models, analyzing their convergence to ideal Bayesian reasoning in probability forecasting tasks.
Contribution
It introduces a formal approach to understanding model management in fallibly rational agents and provides conditions for convergence to larger-world probabilities.
Findings
Conditions for convergence of small-world models to larger-world probabilities
Analysis of search processes over small models as approximations
Framework for managing and revising models in bounded rationality
Abstract
The ideal Bayesian agent reasons from a global probability model, but real agents are restricted to simplified models which they know to be adequate only in restricted circumstances. Very little formal theory has been developed to help fallibly rational agents manage the process of constructing and revising small world models. The goal of this paper is to present a theoretical framework for analyzing model management approaches. For a probability forecasting problem, a search process over small world models is analyzed as an approximation to a larger-world model which the agent cannot explicitly enumerate or compute. Conditions are given under which the sequence of small-world models converges to the larger-world probabilities.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsBayesian Modeling and Causal Inference · Logic, Reasoning, and Knowledge · AI-based Problem Solving and Planning
