下载地址为:http://www.cs.rhul.ac.uk/~chrisw/new_thesis.pdf 论文页面对这篇文章的描述: The thesis introduces the notion of reinforcement learning as learning to control a Markov Decision Process by incremental dynamic programming, and describes a range of algorithms for doing this, including Q-...
2013年,由Volodymyr Mnih、Koray Kavukcuoglu、David Silver等人组成的DeepMind团队,在论文《Playing Atari with Deep Reinforcement Learning》中首次将“深度强化学习”这一术语引入主流学术界。 核心贡献:提出深度Q网络(Deep Q-Network, DQN),首次用卷积神经网络(CNN)直接处理Atari游戏屏幕的像素输入,并通过Q-learning...
该论文的页面为: http://www.cs.rhul.ac.uk/~chrisw/thesis.html 下载地址为: http://www.cs.rhul.ac.uk/~chrisw/new_thesis.pdf 论文页面对这篇文章的描述: The thesis introduces the notion of reinforcement learning as learning to control a Markov Decision Process...