English

Implementing Inductive bias for different navigation tasks through diverse RNN attractors

Neurons and Cognition 2020-02-10 v1

Abstract

Navigation is crucial for animal behavior and is assumed to require an internal representation of the external environment, termed a cognitive map. The precise form of this representation is often considered to be a metric representation of space. An internal representation, however, is judged by its contribution to performance on a given task, and may thus vary between different types of navigation tasks. Here we train a recurrent neural network that controls an agent performing several navigation tasks in a simple environment. To focus on internal representations, we split learning into a task-agnostic pre-training stage that modifies internal connectivity and a task-specific Q learning stage that controls the network's output. We show that pre-training shapes the attractor landscape of the networks, leading to either a continuous attractor, discrete attractors or a disordered state. These structures induce bias onto the Q-Learning phase, leading to a performance pattern across the tasks corresponding to metric and topological regularities. By combining two types of networks in a modular structure, we could get better performance for both regularities. Our results show that, in recurrent networks, inductive bias takes the form of attractor landscapes -- which can be shaped by pre-training and analyzed using dynamical systems methods. Furthermore, we demonstrate that non-metric representations are useful for navigation tasks, and their combination with metric representation leads to flexibile multiple-task learning.

Keywords

Cite

@article{arxiv.2002.02496,
  title  = {Implementing Inductive bias for different navigation tasks through diverse RNN attractors},
  author = {Tie Xu and Omri Barak},
  journal= {arXiv preprint arXiv:2002.02496},
  year   = {2020}
}

Comments

Main text: 11 pages, 5 figures. Supplementary: 16 pages, 14 figures, 3 tables. Accepted as a conference paper for ICLR 2020

R2 v1 2026-06-23T13:33:34.411Z