Biologically plausible multi-dimensional reinforcement learning in neural networks

Authors:
Jaldert O. Rombouts;Arjen van Ooyen;Pieter R. Roelfsema;Sander M. Bohte
Affiliations:
Centrum Wiskunde & Informatica, Amsterdam, The Netherlands;VU University Amsterdam, Amsterdam, The Netherlands;VU University Amsterdam, Amsterdam, The Netherlands,Netherlands Institute for Neuroscience, Amsterdam, The Netherlands;Centrum Wiskunde & Informatica, Amsterdam, The Netherlands
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I
Year:
2012

Citing 5
Cited 0

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Machine Learning
HQ-learning

Adaptive Behavior
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Attention-Gated Reinforcement Learning of Internal Representations for Classification

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

How does the brain learn to map multi-dimensional sensory inputs to multi-dimensional motor outputs when it can only observe single rewards for the coordinated outputs of the whole network of neurons that make up the brain? We introduce Multi-AGREL, a novel, biologically plausible multi-layer neural network model for multi-dimensional reinforcement learning. We demonstrate that Multi-AGREL can learn non-linear mappings from inputs to multi-dimensional outputs by using only scalar reward feedback. We further show that in Multi-AGREL, the changes in the connection weights follow the gradient that minimizes global prediction error, and that all information required for synaptic plasticity is locally present.