Summary of Dynamic Operator Management in Meta-heuristics Using Reinforcement Learning: An Application to Permutation Flowshop Scheduling Problems, by Maryam Karimi Mamaghan et al.
Dynamic operator management in meta-heuristics using reinforcement learning: an application to permutation flowshop scheduling problems
by Maryam Karimi Mamaghan, Mehrdad Mohammadi, Wout Dullaert, Daniele Vigo, Amir Pirayesh
First submitted to arxiv on: 27 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This study introduces a reinforcement learning-based framework for dynamically managing search operators within meta-heuristics, which enables continuous adaptation by updating the portfolio composition during the search. The framework uses a Q-learning-based adaptive operator selection mechanism to select the most suitable operator from the dynamic portfolio at each stage, without requiring input from experts regarding the search operators. The proposed framework is applied to the permutation flowshop scheduling problem and outperforms state-of-the-art algorithms in terms of optimality gap and convergence speed. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study creates a new way for computers to solve hard problems by managing many search tools at once. It uses machine learning to decide which tool to use next, based on how well each one is doing. This approach doesn’t need experts to tell it which tools to use, making it easier for people without expertise to solve problems like scheduling tasks in a factory. |
Keywords
» Artificial intelligence » Machine learning » Reinforcement learning
