PyReason

Read the latest PyReason docs here: https://pyreason.readthedocs.io/en/latest

PyReason Introduction:

• Supports generalized annotated logic with temporal, graphical and uncertainty extensions, capturing a wide variety of fuzzy, real-valued, interval, and temporal logics

• Modern Python-based system supporting reasoning on graph-based data structures (e.g., exported from Neo4j, GraphML, etc.)

• Rule-based reasoning in a manner that support uncertainty, open-world reasoning, non-ground rules, quantification, etc., agnostic to selection of t-norm, etc.

• Fast, highly optimized, correct fixpoint-based deduction allows for explainable AI reasoning, scales to graphs with over 30 million edges

PyReason Paper

https://arxiv.org/pdf/2302.13482.pdf

PyReason Introductory Tutorials

Watch the following introductory videos to learn how to use PyReason with real code examples.

Papers Using PyReason

Geospatial Trajectory Generation via Efficient Abduction: Deployment for Independent Testing (2024)

Preprint: https://arxiv.org/abs/2407.06447
ICLP Talk: https://www.youtube.com/watch?v=8nxuIaTpZzM&ab_channel=NeuroSymbolic

The ability to generate artificial human movement patterns while meeting location and time constraints is an important problem in the security community, particularly as it enables the study of the analog problem of detecting such patterns while maintaining privacy. We frame this problem as an instance of abduction guided by a novel parsimony function represented as an aggregate truth value over an annotated logic program. This approach has the added benefit of affording explainability to an analyst user. By showing that any subset of such a program can provide a lower bound on this parsimony requirement, we are able to abduce movement trajectories efficiently through an informed (i.e., A*) search. We describe how our implementation was enhanced with the application of multiple techniques in order to be scaled and integrated with a cloud-based software stack that included bottom-up rule learning, geolocated knowledge graph retrieval/management, and interfaces with government systems for independently conducted government-run tests for which we provide results. We also report on our own experiments showing that we not only provide exact results but also scale to very large scenarios and provide realistic agent trajectories that can go undetected by machine learning anomaly detectors.

Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning (2024)

Preprint: https://arxiv.org/abs/2310.06835
Code for PyReason-as-a-Sim (integration with DQN): https://github.com/lab-v2/pyreason-rl-sim
Code for PyReason Gym: https://github.com/lab-v2/pyreason-gymlink to paer: https://arxiv.org/abs/2310.06835

Recent advances in reinforcement learning (RL) have shown much promise across a variety of applications. However, issues such as scalability, explainability, and Markovian assumptions limit its applicability in certain domains. We observe that many of these shortcomings emanate from the simulator as opposed to the RL training algorithms themselves. As such, we propose a semantic proxy for simulation based on a temporal extension to annotated logic. In comparison with two high-fidelity simulators, we show up to three orders of magnitude speed-up while preserving the quality of policy learned. In addition, we show the ability to model and leverage non-Markovian dynamics and instantaneous actions while providing an explainable trace describing the outcomes of the agent actions.

Read the PyReason paper (w. supplement):
https://arxiv.org/pdf/2302.13482.pdf

Introductory blog post:
https://medium.com/towards-nesy/pyreason-software-for-open-world-temporal-logic-d67de751830e

PyReason docs: https://pyreason.readthedocs.io/en/latest

Open source Python library is available at: pypi.org/project/pyreason

PyReason codebase can be found at:
github.com/lab-v2/pyreason

Install with pip:
pip install pyreason

Videos:
Introduction: https://youtu.be/E1PSl3KQCmo
Technical talk: https://youtu.be/G4-jcb2ktKg

Slides:
Introduction to PyReason v 1.1

Bibtex citation:
@inproceedings{aditya_pyreason_2023,
title = {{PyReason}: Software for Open World Temporal Logic},
booktitle = {{AAAI} Spring Symposium},
author = {Aditya, Dyuman and Mukherji, Kaustuv and Balasubramanian, Srikar and Chaudhary, Abhiraj and Shakarian, Paulo},
year = {2023} }