Hierarchical Learning for Maze Navigation: Emergence of Mental Representations via Second-Order Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912590794326016 |
|---|---|
| author | Manir, Shalima Binta Oates, Tim |
| author_facet | Manir, Shalima Binta Oates, Tim |
| contents | Mental representation, characterized by structured internal models mirroring external environments, is fundamental to advanced cognition but remains challenging to investigate empirically. Existing theory hypothesizes that second-order learning -- learning mechanisms that adapt first-order learning (i.e., learning about the task/domain) -- promotes the emergence of such environment-cognition isomorphism. In this paper, we empirically validate this hypothesis by proposing a hierarchical architecture comprising a Graph Convolutional Network (GCN) as a first-order learner and an MLP controller as a second-order learner. The GCN directly maps node-level features to predictions of optimal navigation paths, while the MLP dynamically adapts the GCN's parameters when confronting structurally novel maze environments. We demonstrate that second-order learning is particularly effective when the cognitive system develops an internal mental map structurally isomorphic to the environment. Quantitative and qualitative results highlight significant performance improvements and robust generalization on unseen maze tasks, providing empirical support for the pivotal role of structured mental representations in maximizing the effectiveness of second-order learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14195 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hierarchical Learning for Maze Navigation: Emergence of Mental Representations via Second-Order Learning Manir, Shalima Binta Oates, Tim Artificial Intelligence Machine Learning Mental representation, characterized by structured internal models mirroring external environments, is fundamental to advanced cognition but remains challenging to investigate empirically. Existing theory hypothesizes that second-order learning -- learning mechanisms that adapt first-order learning (i.e., learning about the task/domain) -- promotes the emergence of such environment-cognition isomorphism. In this paper, we empirically validate this hypothesis by proposing a hierarchical architecture comprising a Graph Convolutional Network (GCN) as a first-order learner and an MLP controller as a second-order learner. The GCN directly maps node-level features to predictions of optimal navigation paths, while the MLP dynamically adapts the GCN's parameters when confronting structurally novel maze environments. We demonstrate that second-order learning is particularly effective when the cognitive system develops an internal mental map structurally isomorphic to the environment. Quantitative and qualitative results highlight significant performance improvements and robust generalization on unseen maze tasks, providing empirical support for the pivotal role of structured mental representations in maximizing the effectiveness of second-order learning. |
| title | Hierarchical Learning for Maze Navigation: Emergence of Mental Representations via Second-Order Learning |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2509.14195 |