English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Quantum computing holds great potential for advancing the limitations ofmachine learning algorithms to handle higher dimensions of data and reduceoverall training parameters in deep learning (DL) models. This study uses atrainable variational quantum circuit (VQC) on a gate-based quantum computingmodel to investigate the potential for quantum benefit in a model-freereinforcement learning problem. Through a comprehensive investigation andevaluation of the current model and capabilities of quantum computers, wedesigned and trained a novel hybrid quantum neural network based on the latestQiskit and PyTorch framework. We compared its performance with a full-classicalCNN with and without an incorporated VQC. Our research provides insights intothe potential of deep quantum learning to solve a maze problem and,potentially, other reinforcement learning problems. We conclude thatreinforcement learning problems can be practical with reasonable trainingepochs. Moreover, a comparative study of full-classical and hybrid quantumneural networks is discussed to understand these two approaches' performance,advantages, and disadvantages to deep-Q learning problems, especially onlarger-scale maze problems larger than 4x4.

Deep-Q Learning with Hybrid Quantum Neural Network on Solving Maze Problems