Lessons from reinforcement learning for biological representations of space

Muryy, A., Narayanaswamy, S., Nardelli, N., Glennerster, A. ORCID: https://orcid.org/0000-0002-8674-2763 and Torr, P. H. S. (2020) Lessons from reinforcement learning for biological representations of space. Vision Research, 174. pp. 79-93. ISSN 0042-6989 doi: 10.1016/j.visres.2020.05.009

Abstract/Summary

Neuroscientists postulate 3D representations in the brain in a variety of different coordinate frames (e.g. 'head-centred', 'hand-centred' and 'world-based'). Recent advances in reinforcement learning demonstrate a quite different approach that may provide a more promising model for biological representations underlying spatial perception and navigation. In this paper, we focus on reinforcement learning methods that reward an agent for arriving at a target image without any attempt to build up a 3D 'map'. We test the ability of this type of representation to support geometrically consistent spatial tasks such as interpolating between learned locations using decoding of feature vectors. We introduce a hand-crafted representation that has, by design, a high degree of geometric consistency and demonstrate that, in this case, information about the persistence of features as the camera translates (e.g. distant features persist) can improve performance on the geometric tasks. These examples avoid Cartesian (in this case, 2D) representations of space. Non-Cartesian, learned representations provide an important stimulus in neuroscience to the search for alternatives to a 'cognitive map'.

Item Type	Article
URI	https://reading-clone.eprints-hosting.org/id/eprint/90944
Identification Number/DOI	10.1016/j.visres.2020.05.009
Refereed	Yes
Divisions	Interdisciplinary Research Centres (IDRCs) > Centre for Integrative Neuroscience and Neurodynamics (CINN) Life Sciences > School of Psychology and Clinical Language Sciences > Neuroscience Interdisciplinary Research Centres (IDRCs) > Centre for Cognition Research (CCR) Life Sciences > School of Psychology and Clinical Language Sciences > Perception and Action
Publisher	Elsevier
Download/View statistics	View download statistics for this item