Agential AI for integrated continual learning, deliberative behavior, and comprehensible models
Keywords: continual learning, deliberative behavior, planning, comprehensibility, agent
TL;DR: Agential AI (AAI) addresses key limitations of current machine learning by integrating planning, ensuring continual learning without knowledge loss, and modeling temporal dynamics, with promising initial results in abstract environments.
Abstract: Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as lack of integration with planning, incomprehensible internal structures, and inability to learn continually without erasing prior knowledge. We present initial design for an AI system, Agential AI (AAI), in principle operating independently or on top of statistical methods, that overcomes all these issues. AAI's core is a learning method that models temporal dynamics with guarantees of completeness, minimality, and continual learning. It integrates this with a behavior algorithm that plans on a learned model and encapsulate high-level behavior patterns. Preliminary experiments on a simple abstract environment show AAI's effectiveness and future potential.
Primary Area: other topics in machine learning (i.e., none of the above)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 12381
Loading