Agential AI for Integrated Continual Learning, Deliberative Behavior, and Comprehensible Models

TL;DR

This paper introduces Agential AI, a novel system that combines continual learning, planning, and interpretable models to address key limitations of current machine learning approaches, demonstrating promising initial results.

Contribution

The paper presents the initial design of Agential AI, integrating continual learning, planning, and explainability, which is a novel combination not previously achieved in AI systems.

Findings

Preliminary experiments show effective learning and planning in simple environments.

Agential AI models temporal dynamics with guarantees of completeness and minimality.

The system demonstrates potential for more integrated and comprehensible AI solutions.

Abstract

Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure, and inability to learn continually. We present the initial design for an AI system, Agential AI (AAI), in principle operating independently or on top of statistical methods, designed to overcome these issues. AAI's core is a learning method that models temporal dynamics with guarantees of completeness, minimality, and continual learning, using component-level variation and selection to learn the structure of the environment. It integrates this with a behavior algorithm that plans on a learned model and encapsulates high-level behavior patterns. Preliminary experiments on a simple environment show AAI's effectiveness and potential.