DEEP REINFORCEMENT LEARNING WITH FAST UPDATING RECURRENT NEURAL NETWORKS AND SLOW UPDATING RECURRENT NEURAL NETWORKS

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. One of the methods includes selecting an action to be performed by the agentusing both a slow updating recurrent neural network and a fast updating recurrent neural network that receives a fast updating input that includes the hidden state of the slow updating recurrent neural network. 用于强化学习的方法、系统和装置，包括编码在计算机存储介质上的计算机程序。方法之一包括使用慢速更新循环神经网络和快速更新循环神经网络两者来选择要由代理执行的动作，该快速更新循环神经网络接收包括慢速更新循环神经网络的隐藏状态的快速更新输入。