Reinforcement Learning with Quantum Variational Circuits

Abstract

The development of quantum computational techniques has advanced greatly in recent years, parallel to the advancements in techniques for deep reinforcement learning. This work explores the potential for quantum computing to facilitate reinforcement learning problems. Quantum computing approaches offer important potential improvements in time and space complexity over traditional algorithms because of its ability to exploit the quantum phenomena of superposition and entanglement. Specifically, we investigate the use of quantum variational circuits, a form of quantum machine learning. We present our techniques for encoding classical data for a quantum variational circuit, we further explore pure and hybrid quantum algorithms for DQN and Double DQN. Our results indicate both hybrid and pure quantum variational circuit have the ability to solve reinforcement learning tasks with a smaller parameter space. These comparison are conducted with two OpenAI Gym environments: CartPole and Blackjack, The success of this work is indicative of a strong future relationship between quantum machine learning and deep reinforcement learning.

Accepted to AIIDE 2020 Updated to better reflect AAAI formatting

References in corpus (12)

• Quantum Computing in the NISQ era and beyond
• Playing Atari with Deep Reinforcement Learning
• Quantum Machine Learning
• Dueling Network Architectures for Deep Reinforcement Learning
• Quantum Convolutional Neural Networks
• Evaluating analytic gradients on quantum hardware
• Dota 2 with Large Scale Deep Reinforcement Learning
• When Entanglement meets Classical Communications: Quantum Teleportation for the Quantum Internet (Invited Paper)
• Agent57: Outperforming the Atari Human Benchmark
• Efficient Scheme for Initializing a Quantum Register with an Arbitrary Superposed State
• Gradients of parameterized quantum gates using the parameter-shift rule and gate decomposition
• Comparison of Reinforcement Learning algorithms applied to the Cart Pole problem

Cited by in corpus (5)

• A Review on Quantum Approximate Optimization Algorithm and its Variants
• Self-Correcting Quantum Many-Body Control using Reinforcement Learning with Tensor Networks
• Uncovering Instabilities in Variational-Quantum Deep Q-Networks
• Quantum reinforcement learning in continuous action space
• Assessing the Impact of Noise on Quantum Neural Networks: An Experimental Analysis