Ukcheol Shin

An Efficient Asynchronous Method for Integrating Evolutionary and\n Gradient-based Policy Search

2020 · arXiv (Cornell University)

Deep reinforcement learning (DRL) algorithms and evolution strategies (ES)\nhave been applied to various tasks, showing excellent performances. These have\nthe opposite properties, with DRL having good sample efficiency and poor\nstability, while ES being vice versa. Recently, …