Hierarchical Learning for Maze Navigation: Emergence of Mental Representations via Second-Order Learning
This addresses the challenge of investigating mental representations in cognition, but it is incremental as it builds on existing theory with a specific implementation.
The paper tackled the problem of empirically validating the hypothesis that second-order learning promotes the emergence of mental representations isomorphic to environments, by proposing a hierarchical architecture with a GCN and MLP for maze navigation, resulting in significant performance improvements and robust generalization on unseen maze tasks.
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.