• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International conference on neural information processing;Annual conference of Asia-Pacific Neural Network Society >Accelerating Deep Q Network by Weighting Experiences
【24h】

Accelerating Deep Q Network by Weighting Experiences

机译：通过加权经验来加速Deep Q网络

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Deep Q Network (DQN) is a reinforcement learning methodl-ogy that uses deep neural networks to approximate the Q-function. Literature reveals that DQN can select better responses than humans. However, DQN requires a lengthy period of time to learn the appropriate actions by using tuples of state, action, reward and next state, called "experience", sampled from its memory. DQN samples them uniformly and randomly, but the experiences are skewed resulting in slow learning because frequent experiences are redundantly sampled but infrequent ones are not. This work mitigates the problem by weighting experiences based on their frequency and manipulating their sampling probability. In a video game environment, the proposed method learned the appropriate responses faster than DQN.
机译：深度Q网络（DQN）是一种强化学习方法，它使用深度神经网络来近似Q函数。文献表明，DQN可以选择比人类更好的反应。但是，DQN需要花费很长的时间来学习通过使用从其内存中采样的状态，操作，奖励和下一个状态（称为“体验”）的元组来学习适当的操作。 DQN对他们进行了统一且随机的采样，但是由于经常性的经验被多余地采样，而很少的经验则没有，因此这些经验被歪曲了，导致学习速度变慢。这项工作通过根据经验的频率加权经验并控制其采样概率来缓解此问题。在视频游戏环境中，所提出的方法比DQN更快地学会了适当的响应。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号