All issues

The haulage of timber from remote logging areas of Siberia is characterized by high transportation costs. Long stretches of unpaved logging roads, seasonal constraints (spring thaw and winter roads), and considerable distances from cutting areas to main transport hubs (50–200 km) make systematic route planning essential.

This paper proposes a mathematical model of the two-echelon vehicle routing problem (2E-VRP) adapted to timber haulage in the macro-region of the Urals and Siberia. The model incorporates variable transportation costs (truck mileage), fixed costs of using each vehicle ($c_{fix}$ = 30 000 RUB per trip), and vehicle-capacity constraints. The problem is transformed into a QUBO (quadratic unconstrained binary optimization) formulation; capacity constraints are integrated through the penalty coefficient $\lambda_{cap}$ = 500. This representation makes the model compatible with modern specialized solvers, including quantum annealers and digital annealers.

The model is tested on the real geography of the Ural and Siberian Federal Districts: 207 nodes in the logistics network, 65 customer enterprises, and 8 main transport hubs. The proposed three-stage “Feasible-First” algorithm constructs a feasible routing plan in 1.7 s and reduces total transportation costs by 69% relative to a baseline genetic algorithm. Subsequent simulated annealing further improves the QUBO objective value by 55%.

Monte Carlo (MC) reinforcement learning suffers from high sample complexity, especially in environments with sparse rewards, large state spaces, and strongly correlated trajectories that reduce the statistical efficiency of return estimation. These well-known limitations often lead to slow convergence and unstable learning dynamics, particularly in settings where only a small fraction of collected trajectories is actually informative for policy improvement. A key challenge is therefore to identify a compact yet diverse subset of episodes that contributes most to the accuracy of value estimates while preserving sufficient exploration of the environment. To address this challenge, we reformulate episode selection as a Quadratic Unconstrained Binary Optimization (QUBO) problem and solve it using quantum-inspired sampling techniques. Our method, MC+ QUBO, inserts a combinatorial filtering step into the standard MC policy-evaluation pipeline: given a batch of trajectories, it selects a subset that maximizes cumulative reward and encourages broad state-space coverage. This selection procedure is expressed as a QUBO model, where linear terms favor high-return episodes, quadratic terms penalize redundancy between trajectories, and additional coupling terms can be used to enforce coverage-related constraints or promote structural diversity. Within this framework, we investigate two black-box QUBO solvers: Simulated Quantum Annealing (SQA), which emulates tunneling-based exploration of the search landscape, and Simulated Bifurcation (SB), a dynamical-systems-based iterative optimization method. Both solvers demonstrate the ability to efficiently navigate the combinatorial structure of the trajectory-selection problem and to handle batch sizes that are otherwise computationally expensive for exhaustive or deterministic search. Experiments in a finite-horizon GridWorld environment show that MC+QUBO consistently outperforms vanilla MC in convergence speed, stability of return estimates, and final policy quality. These results highlight the promise of quantum-inspired optimization as a practical decision-making subroutine within reinforcement-learning algorithms, offering a scalable way to improve sample efficiency without modifying the underlying learning paradigm.