Variational Quantum Reinforcement Learning via Evolutionary Optimization

Recent advance in classical reinforcement learning (RL) and quantum computation (QC) points to a promising direction of performing RL on a quantum computer. However, potential applications in quantum RL are limited by the number of qubits available in the modern quantum devices. Here we present two...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-09
Main Authors: Samuel Yen-Chi Chen, Huang, Chih-Min, Chia-Wei, Hsing, Hsi-Sheng Goan, Kao, Ying-Jer
Format: Article
Language:English
Subjects:
Amplitudes
Cart-pole problem
Circuits
Evolutionary algorithms
Learning
Optimization
Quantum computers
Quantum computing
Qubits (quantum computing)
Tensors
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent advance in classical reinforcement learning (RL) and quantum computation (QC) points to a promising direction of performing RL on a quantum computer. However, potential applications in quantum RL are limited by the number of qubits available in the modern quantum devices. Here we present two frameworks of deep quantum RL tasks using a gradient-free evolution optimization: First, we apply the amplitude encoding scheme to the Cart-Pole problem; Second, we propose a hybrid framework where the quantum RL agents are equipped with hybrid tensor network-variational quantum circuit (TN-VQC) architecture to handle inputs with dimensions exceeding the number of qubits. This allows us to perform quantum RL on the MiniGrid environment with 147-dimensional inputs. We demonstrate the quantum advantage of parameter saving using the amplitude encoding. The hybrid TN-VQC architecture provides a natural way to perform efficient compression of the input dimension, enabling further quantum RL applications on noisy intermediate-scale quantum devices.
ISSN:2331-8422
DOI:10.48550/arxiv.2109.00540