QuantFPFlow: Quantum Amplitude Estimation for Fokker--Planck Policy Optimisation in Continuous Reinforcement Learning

TL;DR

QuantFPFlow introduces a quantum-inspired reinforcement learning framework that leverages amplitude estimation for efficient policy optimization, achieving quadratic speedup and improved exploration in continuous control tasks.

Contribution

It presents a novel quantum-inspired method integrating amplitude estimation into Fokker--Planck RL, enhancing efficiency and exploration in continuous reinforcement learning.

Findings

Achieves quadratic speedup in estimating the FP partition function.

Outperforms Soft Actor-Critic in a multimodal reward task.

Scales more efficiently with dimensionality compared to classical methods.

Abstract

We introduce \textbf{QuantFPFlow}, a reinforcement learning framework that integrates quantum amplitude estimation into the Fokker--Planck~(FP) formulation of stochastic policy optimisation. Classical continuous-space RL agents must estimate the FP partition function $Z = \int e^{-V(\mathbf{x})/D}\,d\mathbf{x}$ at cost $\calO(1/\varepsilon^{2})$; QuantFPFlow replaces this with a Grover-amplified amplitude estimator achieving $\calO(1/\varepsilon)$ -- a provable quadratic speedup. While the full quantum acceleration requires fault-tolerant hardware, the quantum-inspired classical simulation demonstrated here already exhibits the $\calO(1/\varepsilon)$ algorithmic structure. The estimated stationary distribution $\rhostar$ drives a theoretically grounded exploration bonus $\Raug = \Renv + \alpha\log(1/\rhostar(s))$. This bonus steers the agent toward globally optimal regions of multimodal reward landscapes while simultaneously constraining policy variance through FP diffusion matching. On a continuous-control task specifically designed to expose local-optima failure, QuantFPFlow achieves mean reward $1{,}295.7 \pm 423.2$ versus $1{,}284.0 \pm 474.0$ for Soft Actor-Critic~(SAC), while discovering the global optimum \textbf{10.4\,\% more frequently} (33.9\,\% vs.\ 30.7\,\%). Policy entropy remains near $H(\pi)\approx 6.5$\,nats throughout training, whereas SAC collapses to $1.5$\,nats, confirming that FP diffusion matching actively prevents premature convergence. Dimensionality experiments further show computational scaling of $\calO(d^{0.35})$ for QuantFPFlow versus $\calO(d^{0.76})$ for classical FP estimation.