A New MCTS-Based Algorithm for Multi-Objective Flexible Job Shop Scheduling Problem

Abstract

Multi-objective flexible job-shop scheduling problem (MO-FJSP) is very important in both fields of production management and combinatorial optimization. Wu et al. proposed a Monte-Carlo Tree Search (MCTS) to solve MO-FJSP and successfully improved the performance of MCTS to find 17 Pareto solutions: 4 of Kacem 4x5, 3 of 10x7, 4 of 8x8, 4 of 10x10, and 2 of 15x10. This paper proposes a new MCTS-based algorithm for MO-FJSP problem by modifying their algorithm. Our experimental results show that our new algorithm significantly outperforms their algorithm for large problems, especially for Kacem 15x10. This shows that the new algorithm tends to have better potential of solving harder MO-FJSP problems.