Evolutionary strategy (ES) algorithms operate by generating a population of potential policies, evaluating the performance of each policy, and then updating the population through a process of selection and reproduction. This process is inspired by natural evolution, where the fittest individuals are more likely to survive and reproduce, passing on their genetic traits to the next generation.
[1] Salimans, Tim, Jonathan Ho, Xi Chen, Szymon Sidor, and Ilya Sutskever. “Evolution strategies as a scalable alternative to reinforcement learning.” arXiv preprint arXiv:1703.03864 (2017). https://arxiv.org/abs/1703.03864