A Threshold-based Scheme for Reinforcement Learning in Neural Networks

TL;DR

This paper introduces a scalable reinforcement learning scheme for neural networks that utilizes node thresholds to enable primary and conditioned reinforcement, offering a biologically inspired alternative to backpropagation for supervised and unsupervised learning.

Contribution

It presents a novel threshold-based learning scheme that incorporates primary and conditioned reinforcement, extending capabilities for long-term strategy formation and robustness.

Findings

Solves linearly inseparable problems using primary reinforcement

Enables long-term strategy through conditioned reinforcement

Provides a biologically inspired deep learning algorithm

Abstract

A generic and scalable Reinforcement Learning scheme for Artificial Neural Networks is presented, providing a general purpose learning machine. By reference to a node threshold three features are described 1) A mechanism for Primary Reinforcement, capable of solving linearly inseparable problems 2) The learning scheme is extended to include a mechanism for Conditioned Reinforcement, capable of forming long term strategy 3) The learning scheme is modified to use a threshold-based deep learning algorithm, providing a robust and biologically inspired alternative to backpropagation. The model may be used for supervised as well as unsupervised training regimes.