Variational Quantum Reinforcement Learning via Evolutionary Optimization

TL;DR

This paper introduces two frameworks for deep quantum reinforcement learning using gradient-free evolution optimization, enabling applications on larger input dimensions and demonstrating quantum advantage in parameter efficiency.

Contribution

It presents a hybrid tensor network-variational quantum circuit architecture and an amplitude encoding scheme for quantum RL, expanding applicability on limited qubit quantum devices.

Findings

Quantum advantage in parameter savings with amplitude encoding

Successful application to Cart-Pole and MiniGrid environments

Efficient input dimension compression with hybrid TN-VQC architecture

Abstract

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.