转自知乎，深度强化学习论文https://zhuanlan.zhihu.com/p/23600620

一. 开山鼻祖DQN 1. Playing Atari with Deep Reinforcement Learning，V. Mnih et al., NIPS Workshop, 2013. php 2. Human-level control through deep reinforcement learning, V. Mnih et al., Nature, 2015.html 二. D

>>阅读原文<<