Welcome to NEORL Website!
Primary contact to report bugs/issues: Majdi I. Radaideh (radaideh@umich.edu)
NEORL (NeuroEvolution Optimisation with Reinforcement Learning) is a set of implementations of hybrid algorithms combining neural networks and evolutionary computation based on a wide range of machine learning and evolutionary intelligence architectures. NEORL aims to solve large-scale optimization problems relevant to operation & optimisation research, engineering, business, and other disciplines.
Github repository: https://github.com/aims-umich/neorl/
NEORL paper: https://doi.org/10.1016/j.nucengdes.2023.112423
Copyright
This repository and its content are copyright of Exelon Corporation © in collaboration with MIT Nuclear Science and Engineering 2021. NEORL is currently maintained by Artificial Intelligence and Multiphysics Simulations (AIMS) Lab at the University of Michigan NERS 2023. All rights reserved.
You can read the first successful application of NEORL for nuclear fuel optimisation in this News Article.
User Guide
- General Guide
- Algorithms
- Hyperparameter Tuning
- Examples
- 1. Example 1: Traveling Salesman Problem
- 2. Example 2: Ackley with EA
- 3. Example 3: Welded-beam design
- 4. Example 4: Benchmarks
- 5. Example 5: CEC’2017 Test Suite
- 6. Example 6: Three-bar Truss Design
- 7. Example 7: Pressure Vessel Design
- 8. Example 8: Pressure Vessel Design with Demonstration of Categorical Parameter
- 9. Example 9: Cantilever Stepped Beam
- 10. Example 10: Knapsack Problem
- 11. Example 11: Microreactor Control with Malfunction
Projects/Papers Using NEORL
1- Erdem, O. F., Price, D., Seurin, P., & Radaideh, M. I. (2026). MAEO: Scalable Multiobjective Animorphic Ensemble Optimization for large-scale optimization applications. Nuclear Engineering and Design, 458, p. 115156 [LINK1].
2- Price, D., Radaideh, M. I. (2023). Animorphic ensemble optimization: a large-scale island model. Neural Computing and Applications, 35(4), 3221-3243 [LINK2].
3- Radaideh, M. I., Du, K., Seurin, P., Seyler, D., Gu, X., Wang, H., & Shirvan, K. (2023). NEORL: NeuroEvolution Optimization with Reinforcement Learning—Applications to carbon-free energy systems. Nuclear Engineering and Design, 412, p. 112423 [LINK3].
4- Radaideh, M. I., Wolverton, I., Joseph, J., Tusar, J. J., Otgonbaatar, U., Roy, N., Forget, B., Shirvan, K. (2021). Physics-informed reinforcement learning optimization of nuclear assembly design. Nuclear Engineering and Design, 372, p. 110966 [LINK4].
5- Radaideh, M. I., Shirvan, K. (2021). Rule-based reinforcement learning methodology to inform evolutionary algorithms for constrained optimization of engineering applications. Knowledge-Based Systems, 217, p. 106836 [LINK5].
6- Radaideh, M. I., Forget, B., Shirvan, K. (2021). Large-scale design optimisation of boiling water reactor bundles with neuroevolution. Annals of Nuclear Energy, 160, 108355 [LINK6].
Citing the Project
To cite this repository in publications:
@article{radaideh2023neorl,
title={NEORL: NeuroEvolution Optimization with Reinforcement Learning—Applications to carbon-free energy systems},
author={Radaideh, Majdi I and Du, Katelin and Seurin, Paul and Seyler, Devin and Gu, Xubo and Wang, Haijia and Shirvan, Koroush},
journal={Nuclear Engineering and Design},
volume={412},
pages={112423},
year={2023},
publisher={Elsevier}
}
Acknowledgments
NEORL was established in MIT back to 2020 with feedback, validation, and usage of different colleagues: Issac Wolverton (MIT Quest for Intelligence), Joshua Joseph (MIT Quest for Intelligence), Benoit Forget (MIT Nuclear Science and Engineering), Ugi Otgonbaatar (Exelon Corporation).
In January 2023, a University of Michigan team took over maintaining this repository after its founder, Majdi Radadideh, joined their faculty. Now NEORL is part of the Artificial Intelligence and Multiphysics Simulations (AIMS) Lab at the University of Michigan NERS.