BriefGPT.xyz
Dec, 2013
使用深度强化学习玩Atari游戏
Playing Atari with Deep Reinforcement Learning
HTML
PDF
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou...
TL;DR
本文介绍了一种使用卷积神经网络和增强学习从高维感知输入中直接学习控制策略的深度学习模型,并将其应用于七个 Atari 2600 游戏中,发现在 6 个游戏上优于以往的方法,在其中三个游戏中超过了人类专家。
Abstract
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
→