Variational Quantum Circuits for Deep Reinforcement Learning

By Samuel Yen-Chi Chen et al

Read the original document by opening this link in a new tab.

Table of Contents

ABSTRACT
INDEX TERMS
I. INTRODUCTION
II. REINFORCEMENT LEARNING
A. Q-LEARNING
B. STATE-ACTION-REWARD-STATE-ACTION (SARSA)
C. DEEP Q-LEARNING
III. TESTING ENVIRONMENTS
A. FROZEN LAKE
B. COGNITIVE RADIO

Summary

The document discusses the use of variational quantum circuits for deep reinforcement learning. It explores reshaping classical deep reinforcement learning algorithms into quantum circuits and the encoding scheme to reduce model parameters. The work is the first proof-of-principle demonstration of variational quantum circuits for decision-making and policy-selection reinforcement learning. The paper also addresses the challenges of using quantum computing platforms for deep learning models and proposes feasible quantum algorithms for quantum machine learning. It delves into the frozen-lake and cognitive-radio environments to demonstrate the application of variational quantum circuits in different scenarios.