NEORL: NeuroEvolution Optimization with Reinforcement Learning—Applications to carbon-free energy systems

Abstract

We present an open-source Python framework for NeuroEvolution Optimization with Reinforcement Learning (NEORL) developed at the Massachusetts Institute of Technology. NEORL offers a global optimization interface of state-of-the-art algorithms in the field of evolutionary computation, neural networks through reinforcement learning, and hybrid neuroevolution algorithms. NEORL features diverse set of algorithms, user-friendly interface, parallel computing support, automatic hyperparameter tuning, detailed documentation, and demonstration of applications in mathematical and real-world engineering optimization. NEORL encompasses various optimization problems from combinatorial, continuous, mixed discrete/continuous, to high-dimensional, expensive, and constrained engineering optimization. In this paper, NEORL is tested in a variety of engineering applications relevant to low carbon energy research in addressing solutions to climate change. The examples include nuclear reactor control, nuclear fuel optimization, mechanical and structural design optimization, and fuel cell power production. The results demonstrate NEORL competitiveness against other algorithms and optimization frameworks in the literature, and a potential tool to solve large-scale optimization problems. More details about NEORL can be found here: https://neorl.readthedocs.io/en/latest/index.html.