Tyche: A library for probabilistic reasoning and belief modelling in Python

TL;DR

Tyche is a Python library that enables probabilistic reasoning and belief modeling using aleatoric description logic, supporting learning from observations and applications in author identification and knowledge extraction.

Contribution

The paper introduces Tyche, a novel Python library utilizing ADL for efficient probabilistic reasoning, belief modeling, and learning from complex observations.

Findings

Successfully predicted authors of anonymised messages.

Extracted author writing tendencies from data.

Demonstrated potential in expert systems and game agents.

Abstract

This paper presents Tyche, a Python library to facilitate probabilistic reasoning in uncertain worlds through the construction, querying, and learning of belief models. Tyche uses aleatoric description logic (ADL), which provides computational advantages in its evaluation over other description logics. Tyche belief models can be succinctly created by defining classes of individuals, the probabilistic beliefs about them (concepts), and the probabilistic relationships between them (roles). We also introduce a method of observation propagation to facilitate learning from complex ADL observations. A demonstration of Tyche to predict the author of anonymised messages, and to extract author writing tendencies from anonymised messages, is provided. Tyche has the potential to assist in the development of expert systems, knowledge extraction systems, and agents to play games with incomplete and probabilistic information.