Playing Atari with Deep Reinforcement Learning
Playing Atari with Deep Reinforcement Learning
复制标题
DOI：
--
复制
发表时间：
2013-12
期刊：
影响因子：
--
通讯作者：
Volodymyr Mnih;K. Kavukcuoglu;David Silver;Alex Graves;Ioannis Antonoglou;Daan Wierstra;Martin A. Riedmiller-Martin-A
中科院分区：
文献类型：
--
作者：
Volodymyr Mnih;K. Kavukcuoglu;David Silver;Alex Graves;Ioannis Antonoglou;Daan Wierstra;Martin A. Riedmiller-Martin-A
我们提出了第一个使用强化学习直接从高维感官输入成功学习控制策略的深度学习模型。该模型是一个卷积神经网络，用q学习的一种变体进行训练，其输入是原始像素，输出是估计未来奖励的价值函数。我们将自己的方法应用于街机学习环境中的7款Atari 2600游戏，没有调整架构或学习算法。我们发现，它在6个游戏中胜过了所有以前的方法，在3个游戏中超过了人类专家。
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.