Self-Guided Evolution Strategies with Historical Estimated Gradients

1 code implementation • IJCAI 2020 • Fei-Yu Liu, Zi-Niu Li, Chao Qian

Evolution Strategies (ES) are a class of black-box optimization algorithms and have been widely applied to solve problems, e. g., in reinforcement learning (RL), where the true gradient is unavailable.

Reinforcement Learning (RL)