QTRL: Toward Practical Quantum Reinforcement Learning via Quantum-Train

TL;DR

This paper introduces QTRL, a quantum training method for reinforcement learning that reduces parameters and enables classical inference, making quantum-enhanced RL more practical and cost-efficient.

Contribution

QTRL applies quantum training to reinforcement learning, eliminating data encoding issues and enabling classical inference with fewer parameters, improving practicality and efficiency.

Findings

Reduces classical policy network parameters via quantum training.

Eliminates data encoding challenges in quantum reinforcement learning.

Enables classical inference, improving practicality and cost-efficiency.

Abstract

Quantum reinforcement learning utilizes quantum layers to process information within a machine learning model. However, both pure and hybrid quantum reinforcement learning face challenges such as data encoding and the use of quantum computers during the inference stage. We apply the Quantum-Train method to reinforcement learning tasks, called QTRL, training the classical policy network model using a quantum machine learning model with polylogarithmic parameter reduction. This QTRL approach eliminates the data encoding issues of conventional quantum machine learning and reduces the training parameters of the corresponding classical policy network. Most importantly, the training result of the QTRL is a classical model, meaning the inference stage only requires classical computer. This is extremely practical and cost-efficient for reinforcement learning tasks, where low-latency feedback from the policy model is essential.