UCL Discovery Stage
UCL home » Library Services » Electronic resources » UCL Discovery Stage

Prediction and generalisation over directed actions by grid cells

Yu, C; Behrens, TEJ; Burgess, N; (2021) Prediction and generalisation over directed actions by grid cells. In: Proceedings of ICLR 2021 - 9th International Conference on Learning Representations. Green open access

[thumbnail of 1555_prediction_and_generalisation_.pdf]
Preview
Text
1555_prediction_and_generalisation_.pdf - Published Version

Download (1MB) | Preview

Abstract

Knowing how the effects of directed actions generalise to new situations (e.g. moving North, South, East and West, or turning left, right, etc.) is key to rapid generalisation across new situations. Markovian tasks can be characterised by a state space and a transition matrix and recent work has proposed that neural grid codes provide an efficient representation of the state space, as eigenvectors of a transition matrix reflecting diffusion across states, that allows efficient prediction of future state distributions. Here we extend the eigenbasis prediction model, utilising tools from Fourier analysis, to prediction over arbitrary translation-invariant directed transition structures (i.e. displacement and diffusion), showing that a single set of eigenvectors can support predictions over arbitrary directed actions via action-specific eigenvalues. We show how to define a "sense of direction" to combine actions to reach a target state (ignoring task-specific deviations from translation-invariance), and demonstrate that adding the Fourier representations to a deep Q network aids policy learning in continuous control tasks. We show the equivalence between the generalised prediction framework and traditional models of grid cell firing driven by self-motion to perform path integration, either using oscillatory interference (via Fourier components as velocity-controlled oscillators) or continuous attractor networks (via analysis of the update dynamics). We thus provide a unifying framework for the role of the grid system in predictive planning, sense of direction and path integration: supporting generalisable inference over directed actions across different tasks.

Type: Proceedings paper
Title: Prediction and generalisation over directed actions by grid cells
Event: ICLR 2021 - 9th International Conference on Learning Representations
Open access status: An open access version is available from UCL Discovery
Publisher version: https://openreview.net/forum?id=Ptaz_zIFbX
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > UCL Queen Square Institute of Neurology
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Brain Sciences > UCL Queen Square Institute of Neurology > Clinical and Experimental Epilepsy
URI: https://discovery-pp.ucl.ac.uk/id/eprint/10168096
Downloads since deposit
468Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item