Cognitive map formation under uncertainty via local prediction learning
Keywords: cognitive maps, local prediction learning, vector symbolic architectures
Abstract: Cognitive maps are internal world models that enable adaptive behavior including spatial navigation and planning. The Cognitive Map Learner (CML) has been recently proposed as a model for cognitive map formation and planning. A CML learns high dimensional state and action representations using local prediction learning. While the CML offers a simple and elegant solution to cognitive map learning, it is limited by its simplicity, applying only to fully observable environments. To address this, we introduce the Partially Observable Cognitive Map Learner (POCML), extending the CML to handle partially observable environments.
The POCML employs a superposition of states for probabilistic representation and uses binding operations for state updates. Additionally, an associative memory is incorporated to enable adaptive behavior across environments with similar structures. We derive local update rules tailored to the POCML's probabilistic state representation and associative memory. We demonstrate a POCML is capable of learning the underlying structure of an environment via local next-observation prediction learning. In addition, we show that a POCML trained on an environment is capable of generalizing to environments with the same underlying structure but with novel observations, achieving good zero-shot next-observation prediction accuracy, significantly outperforming sequence models such as LSTMs and Transformers. Finally, we present a case study of navigation in a two-tunnel maze environment with aliased observations, showing that a POCML is capable of effectively using its probabilistic state representations for disambiguation of states and spatial navigation.
Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning
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.
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: 11177
Loading