Quantum reinforcement learning in continuous action space

TL;DR

This paper introduces a quantum deep deterministic policy gradient algorithm that enables efficient reinforcement learning in continuous action spaces and allows for single-shot quantum state generation, improving quantum control methods.

Contribution

It presents a novel quantum reinforcement learning algorithm for continuous actions and demonstrates its capability for single-shot quantum state generation, addressing limitations of existing methods.

Findings

Effective in simulations for quantum control tasks

Enables one-time optimization for multiple target states

Outperforms traditional quantum control approaches

Abstract

Quantum reinforcement learning (QRL) is a promising paradigm for near-term quantum devices. While existing QRL methods have shown success in discrete action spaces, extending these techniques to continuous domains is challenging due to the curse of dimensionality introduced by discretization. To overcome this limitation, we introduce a quantum Deep Deterministic Policy Gradient (DDPG) algorithm that efficiently addresses both classical and quantum sequential decision problems in continuous action spaces. Moreover, our approach facilitates single-shot quantum state generation: a one-time optimization produces a model that outputs the control sequence required to drive a fixed initial state to any desired target state. In contrast, conventional quantum control methods demand separate optimization for each target state. We demonstrate the effectiveness of our method through simulations and discuss its potential applications in quantum control.