Dynamic operator management in meta-heuristics using reinforcement learning: an application to permutation flowshop scheduling problems
This addresses the need for non-experts to effectively use meta-heuristics in scheduling problems, though it is incremental as it builds on existing reinforcement learning and tabu search methods.
This study tackled the problem of dynamically managing search operators in meta-heuristics by developing a reinforcement learning framework that adapts operator portfolios, applied to permutation flowshop scheduling, resulting in superior performance against state-of-the-art algorithms in optimality gap and convergence speed.
This study develops a framework based on reinforcement learning to dynamically manage a large portfolio of search operators within meta-heuristics. Using the idea of tabu search, the framework allows for continuous adaptation by temporarily excluding less efficient operators and updating the portfolio composition during the search. A Q-learning-based adaptive operator selection mechanism is used to select the most suitable operator from the dynamically updated portfolio at each stage. Unlike traditional approaches, the proposed framework requires no input from the experts regarding the search operators, allowing domain-specific non-experts to effectively use the framework. The performance of the proposed framework is analyzed through an application to the permutation flowshop scheduling problem. The results demonstrate the superior performance of the proposed framework against state-of-the-art algorithms in terms of optimality gap and convergence speed.