Agential AI for Integrated Continual Learning, Deliberative Behavior, and Comprehensible Models
This addresses the problem of integrated, comprehensible, and continual AI systems for researchers and practitioners, but it appears incremental as it builds on existing statistical methods.
The paper tackles the limitations of contemporary machine learning, such as lack of planning integration and inability to learn continually, by proposing Agential AI (AAI), with preliminary experiments on a simple environment showing its effectiveness and potential.
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.