• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Learning With Stochastic Guidance for Robot Navigation
【24h】

Learning With Stochastic Guidance for Robot Navigation

机译：利用机器人导航随机指导

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Due to the sparse rewards and high degree of environmental variation, reinforcement learning approaches, such as deep deterministic policy gradient (DDPG), are plagued by issues of high variance when applied in complex real-world environments. We present a new framework for overcoming these issues by incorporating a stochastic switch, allowing an agent to choose between high- and low-variance policies. The stochastic switch can be jointly trained with the original DDPG in the same framework. In this article, we demonstrate the power of the framework in a navigation task, where the robot can dynamically choose to learn through exploration or to use the output of a heuristic controller as guidance. Instead of starting from completely random actions, the navigation capability of a robot can be quickly bootstrapped by several simple independent controllers. The experimental results show that with the aid of stochastic guidance, we are able to effectively and efficiently train DDPG navigation policies and achieve significantly better performance than state-of-the-art baseline models.
机译：由于稀疏奖励和高度的环境变化，加强学习方法，如深度确定性政策梯度（DDPG），在复杂的真实环境中应用时，在高方差时受到高方差的问题。我们通过结合随机交换机来介绍一种克服这些问题的新框架，允许代理在高方差和低方差策略之间进行选择。随机开关可以在同一框架中与原始DDPG共同训练。在本文中，我们展示了导航任务中框架的力量，其中机器人可以动态选择通过探索学习或使用启发式控制器的输出作为指导。而不是从完全随机动作开始，可以通过几个简单的独立控制器快速启动机器人的导航能力。实验结果表明，借助随机指导，我们能够有效且有效地培训DDPG导航政策，而不是最先进的基线模型实现明显更好的性能。

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