Representing and Reasoning With Probabilistic Knowledge: A Bayesian Approach

TL;DR

This paper introduces PAGODA, a Bayesian model for autonomous learning that uses probabilistic theories and a novel inference mechanism to predict outcomes in uncertain environments.

Contribution

It presents a new probabilistic representation and inference method for autonomous agents to learn and reason about their environment using Bayesian theories.

Findings

PAGODA effectively forms theories about actions and world states.

The PCI inference mechanism combines probabilities with minimal independence assumptions.

The approach enables unique probabilistic predictions for actions and states.

Abstract

PAGODA (Probabilistic Autonomous Goal-Directed Agent) is a model for autonomous learning in probabilistic domains [desJardins, 1992] that incorporates innovative techniques for using the agent's existing knowledge to guide and constrain the learning process and for representing, reasoning with, and learning probabilistic knowledge. This paper describes the probabilistic representation and inference mechanism used in PAGODA. PAGODA forms theories about the effects of its actions and the world state on the environment over time. These theories are represented as conditional probability distributions. A restriction is imposed on the structure of the theories that allows the inference mechanism to find a unique predicted distribution for any action and world state description. These restricted theories are called uniquely predictive theories. The inference mechanism, Probability Combination using Independence (PCI), uses minimal independence assumptions to combine the probabilities in a theory to make probabilistic predictions.