An Adaptive Operator Selection method based on Double Deep Q-Learning (DDQN), a Deep Reinforcement Learning method, to control the mutation strategies of Differential Evolution (DE).
Dependencies required: Keras, gym, keras-rl, optproblems
If you use this repository, please cite the following paper:
@inproceedings{sharma2019deep,
title={Deep reinforcement learning based parameter control in differential evolution},
author={Sharma, Mudita and Komninos, Alexandros and L{\'o}pez-Ib{\'a}{\~n}ez, Manuel and Kazakov, Dimitar},
booktitle={Proceedings of the Genetic and Evolutionary Computation Conference},
pages={709--717},
year={2019}
}