Quantum-Inspired Episode Selection for Monte Carlo Reinforcement Learning via QUBO Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Salloum, Hadi, Jnadi, Ali, Kholodov, Yaroslav, Gasnikov, Alexander
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914277762269184
author Salloum, Hadi
Jnadi, Ali
Kholodov, Yaroslav
Gasnikov, Alexander
author_facet Salloum, Hadi
Jnadi, Ali
Kholodov, Yaroslav
Gasnikov, Alexander
contents Monte Carlo (MC) reinforcement learning suffers from high sample complexity, especially in environments with sparse rewards, large state spaces, and correlated trajectories. We address these limitations by reformulating episode selection as a Quadratic Unconstrained Binary Optimization (QUBO) problem and solving it with quantum-inspired samplers. Our method, MC+QUBO, integrates a combinatorial filtering step into standard MC policy evaluation: from each batch of trajectories, we select a subset that maximizes cumulative reward while promoting state-space coverage. This selection is encoded as a QUBO, where linear terms favor high-reward episodes and quadratic terms penalize redundancy. We explore both Simulated Quantum Annealing (SQA) and Simulated Bifurcation (SB) as black-box solvers within this framework. Experiments in a finite-horizon GridWorld demonstrate that MC+QUBO outperforms vanilla MC in convergence speed and final policy quality, highlighting the potential of quantum-inspired optimization as a decision-making subroutine in reinforcement learning.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17570
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Quantum-Inspired Episode Selection for Monte Carlo Reinforcement Learning via QUBO Optimization
Salloum, Hadi
Jnadi, Ali
Kholodov, Yaroslav
Gasnikov, Alexander
Machine Learning
Robotics
Monte Carlo (MC) reinforcement learning suffers from high sample complexity, especially in environments with sparse rewards, large state spaces, and correlated trajectories. We address these limitations by reformulating episode selection as a Quadratic Unconstrained Binary Optimization (QUBO) problem and solving it with quantum-inspired samplers. Our method, MC+QUBO, integrates a combinatorial filtering step into standard MC policy evaluation: from each batch of trajectories, we select a subset that maximizes cumulative reward while promoting state-space coverage. This selection is encoded as a QUBO, where linear terms favor high-reward episodes and quadratic terms penalize redundancy. We explore both Simulated Quantum Annealing (SQA) and Simulated Bifurcation (SB) as black-box solvers within this framework. Experiments in a finite-horizon GridWorld demonstrate that MC+QUBO outperforms vanilla MC in convergence speed and final policy quality, highlighting the potential of quantum-inspired optimization as a decision-making subroutine in reinforcement learning.
title Quantum-Inspired Episode Selection for Monte Carlo Reinforcement Learning via QUBO Optimization
topic Machine Learning
Robotics
url https://arxiv.org/abs/2601.17570