...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>JMLR: Workshop and Conference Proceedings >Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling
【24h】

Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling

机译：连续动作空间中的深度强化学习：以模拟冰壶游戏为例

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

摘要

Many real-world applications of reinforcement learning require an agent to select optimal actions from continuous spaces. Recently, deep neural networks have successfully been applied to games with discrete actions spaces. However, deep neural networks for discrete actions are not suitable for devising strategies for games where a very small change in an action can dramatically affect the outcome. In this paper, we present a new self-play reinforcement learning framework which equips a continuous search algorithm which enables to search in continuous action spaces with a kernel regression method. Without any hand-crafted features, our network is trained by supervised learning followed by self-play reinforcement learning with a high-fidelity simulator for the Olympic sport of curling. The program trained under our framework outperforms existing programs equipped with several hand-crafted features and won an international digital curling competition.
机译：增强学习的许多实际应用都需要代理从连续空间中选择最佳动作。最近，深度神经网络已成功应用于具有离散动作空间的游戏。然而，用于离散动作的深度神经网络不适用于设计游戏策略，在这种策略中，动作的很小变化会严重影响结果。在本文中，我们提出了一种新的自我扮演强化学习框架，该框架配备了一种连续搜索算法，该算法可以使用核回归方法在连续动作空间中进行搜索。由于没有任何手工制作的功能，我们的网络在监督学习的基础上进行训练，然后通过高保真模拟器进行自我练习强化学习，以进行奥林匹克冰壶运动。在我们的框架下训练的程序胜过配备了几个手工功能的现有程序，并赢得了国际数字冰壶比赛。

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