论文笔记：《Playing Atari with Deep Reinforcement Learning》
文章摘要：本文是第一篇使用深度学习和强化学习结合起来的模型的论文。作者采用CNN作为深度学习模型，结合Q-Learning强化学习算法进行训练。CNN的输入为高维原始像素，输出为估计期望奖赏的估值函数。通过本文训练的神经网络在7个Atari 2600游戏上的得分有6个胜过了以往最好方法，有3个游戏超过了人类专家。 深度学习与强化学习的结合： 一方面，强化学习在视频和语音方面的主要困难在于，学习
相关文章
- 1. 【论文翻译】Playing Atari with Deep Reinforcement Learning
- 2. Playing Atari with Deep Reinforcement Learning
- 3. Playing atari with deep reinforcement learning
- 4. Playing Atari with Deep Reinforcement Learning 中文 讲解
- 5. NIPS-2013：Playing Atari with Deep Reinforcement Learning
- 6. Paper reading: Playing Atari with Deep Reinforcement Learning
- 7. 【5分钟 Paper】Playing Atari with Deep Reinforcement Learning
- 8. RL论文阅读【一】Playing Atari with Deep Reinforcement Learning
- 9. 论文笔记 Reinforcement Learning with Derivative-Free Exploration
- 10. 【5分钟 Paper】Continuous Control With Deep Reinforcement Learning
- 更多相关文章...
- • ASP.NET Razor - 标记 - ASP.NET 教程
- • CAP理论是什么？ - NoSQL教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • Scala 中文乱码解决
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 【论文翻译】Playing Atari with Deep Reinforcement Learning
- 2. Playing Atari with Deep Reinforcement Learning
- 3. Playing atari with deep reinforcement learning
- 4. Playing Atari with Deep Reinforcement Learning 中文 讲解
- 5. NIPS-2013：Playing Atari with Deep Reinforcement Learning
- 6. Paper reading: Playing Atari with Deep Reinforcement Learning
- 7. 【5分钟 Paper】Playing Atari with Deep Reinforcement Learning
- 8. RL论文阅读【一】Playing Atari with Deep Reinforcement Learning
- 9. 论文笔记 Reinforcement Learning with Derivative-Free Exploration
- 10. 【5分钟 Paper】Continuous Control With Deep Reinforcement Learning