Performing Deep Recurrent Double Q-Learning for Atari Games
Performing Deep Recurrent Double Q-Learning for Atari Games
复制标题
为 Atari 游戏执行深度循环双 Q 学习
DOI：
10.1109/la-cci47412.2019.9036763
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Felipe Moreno
中科院分区：
文献类型：
--
作者：
Felipe Moreno
目前，机器学习中的许多应用都是基于定义新模型来提取有关数据的更多信息，在这种情况下，深度强化学习与Atari，Mario等视频游戏中最常见的应用对计算机如何通过从任何动作中获得的称为奖励的信息进行自我学习产生了影响。在AlphaZero和Go中，有很多基于DeepMind提出的深度递归Q-Learning建模和实现的算法。在本文中，我们提出了深度递归双Q学习，这是对双Q学习算法和递归网络（如LSTM和DRQN）的改进。
Currently, many applications in Machine Learning are based on defining new models to extract more information about data, In this case Deep Reinforcement Learning with the most common application in video games like Atari, Mario, and others causes an impact in how to computers can learning by himself with only information called rewards obtained from any action. There is a lot of algorithms modeled and implemented based on Deep Recurrent Q-Learning proposed by DeepMind used in AlphaZero and Go. In this document, we proposed deep recurrent double Q-learning that is an improvement of the algorithms Double Q-Learning algorithms and Recurrent Networks like LSTM and DRQN.