Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach
This work addresses quantum reinforcement learning for researchers in quantum computing and AI, presenting a novel method with theoretical improvements.
The paper tackles the problem of quantum reinforcement learning under model-free settings by introducing a Quantum Natural Policy Gradient algorithm, which achieves a sample complexity of ε^{-1.5} for quantum oracle queries, improving upon the classical lower bound of ε^{-2}.
We address the problem of quantum reinforcement learning (QRL) under model-free settings with quantum oracle access to the Markov Decision Process (MDP). This paper introduces a Quantum Natural Policy Gradient (QNPG) algorithm, which replaces the random sampling used in classical Natural Policy Gradient (NPG) estimators with a deterministic gradient estimation approach, enabling seamless integration into quantum systems. While this modification introduces a bounded bias in the estimator, the bias decays exponentially with increasing truncation levels. This paper demonstrates that the proposed QNPG algorithm achieves a sample complexity of $\tilde{\mathcal{O}}(ε^{-1.5})$ for queries to the quantum oracle, significantly improving the classical lower bound of $\tilde{\mathcal{O}}(ε^{-2})$ for queries to the MDP.