AIApr 7, 2016

On Stochastic Belief Revision and Update and their Combination

arXiv:1604.02126v16 citations
Originality Incremental advance
AI Analysis

This work addresses belief change in AI systems, but it is incremental as it extends existing qualitative models to a quantitative framework.

The paper tackles the problem of how an agent should change its probabilistic beliefs when new information is observed, by proposing a unified quantitative model that combines revision and update processes, and evaluates it against rationality postulates.

I propose a framework for an agent to change its probabilistic beliefs when a new piece of propositional information $α$ is observed. Traditionally, belief change occurs by either a revision process or by an update process, depending on whether the agent is informed with $α$ in a static world or, respectively, whether $α$ is a 'signal' from the environment due to an event occurring. Boutilier suggested a unified model of qualitative belief change, which "combines aspects of revision and update, providing a more realistic characterization of belief change." In this paper, I propose a unified model of quantitative belief change, where an agent's beliefs are represented as a probability distribution over possible worlds. As does Boutilier, I take a dynamical systems perspective. The proposed approach is evaluated against several rationality postulated, and some properties of the approach are worked out.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes