0


在深层强化学习中玩雅达利

Playing Atari with Deep Reinforcement Learning
课程网址: http://videolectures.net/nipsworkshops2013_mnih_atari/  
主讲教师: Volodymyr Mnih
开课单位: 多伦多大学
开课时间: 2014-10-06
课程语种: 英语
中文简介:

我们提出了第一个深度学习模型,可以使用强化学习直接从高维感官输入中成功学习控制策略。该模型是一个卷积神经网络,通过Q学习的变体进行训练,其输入为原始像素,其输出为估计未来收益的价值函数。我们将我们的方法应用于Arcade学习环境中的七个Atari 2600游戏,无需调整体系结构或学习算法。我们发现它在六个游戏中的表现都优于以前的所有方法,在三个游戏中都超过了人类专家。

课程简介: We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method to seven Atari 2600 games from the Arcade Learning Environment, with no adjustment of the architecture or learning algorithm. We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them.
关 键 词: 深度学习; 控制策略
课程来源: 视频讲座网
数据采集: 2020-11-12:zyk
最后编审: 2020-11-12:zyk
阅读次数: 38