Investigating the Monte-Carlo Tree Search Approach for the Job Shop Scheduling Problem

2025-01-29

AI Summary

This work addresses the NP-hard large-scale job shop scheduling problem (JSSP) with reentrant flows, aiming to minimize weighted makespan. Method: It introduces Monte Carlo Tree Search (MCTS) into this domain for the first time, proposing multiple Markov Decision Process (MDP) formulations and establishing the first large-scale synthetic benchmark grounded in real manufacturing data and supporting non-rectangular operation structures. Contribution/Results: Compared against constraint programming (CP) and reinforcement learning baselines, the proposed MCTS approach achieves significantly higher solution quality and computational efficiency—consistently producing high-quality schedules on instances with over one thousand operations. The core contributions are: (i) empirical validation of MCTS’s effectiveness for complex combinatorial scheduling, and (ii) establishment of a scalable, reproducible JSSP benchmark and modeling paradigm aligned with real-world manufacturing requirements.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

The Job Shop Scheduling Problem (JSSP) is a well-known optimization problem in manufacturing, where the goal is to determine the optimal sequence of jobs across different machines to minimize a given objective. In this work, we focus on minimising the weighted sum of job completion times. We explore the potential of Monte Carlo Tree Search (MCTS), a heuristic-based reinforcement learning technique, to solve large-scale JSSPs, especially those with recirculation. We propose several Markov Decision Process (MDP) formulations to model the JSSP for the MCTS algorithm. In addition, we introduce a new synthetic benchmark derived from real manufacturing data, which captures the complexity of large, non-rectangular instances often encountered in practice. Our experimental results show that MCTS effectively produces good-quality solutions for large-scale JSSP instances, outperforming our constraint programming approach.

Problem

• Monte Carlo Tree Search
• Job Shop Scheduling Problem
• Minimization of Weighted Completion Time

Innovation

• Monte Carlo Tree Search
• Job-Shop Scheduling Problem
• Constraint Programming