...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Adaptive Behavior >Transfer learning by prototype generation in continuous spaces
【24h】

Transfer learning by prototype generation in continuous spaces

机译：在连续空间中通过原型生成转移学习

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

In machine learning, learning a task is expensive (many training samples are needed) and it is therefore of general interest to be able to reuse knowledge across tasks. This is the case in aerial robotics applications, where an autonomous aerial robot cannot interact with the environment hazard free. Prototype generation is a well known technique commonly used in supervised learning to help reduce the number of samples needed to learn a task. However, little is known about how such techniques can be used in a reinforcement learning task. In this work we propose an algorithm that, in order to learn a new (target) task, first generates new samplesprototypesbased on samples acquired previously in a known (source) task. The proposed approach uses Gaussian processes to learn a continuous multidimensional transition function, rendering the method capable of reasoning directly in continuous (states and actions) domains. We base the prototype generation on a careful selection of a subset of samples from the source task (based on known filtering techniques) and transforming such samples using the (little) knowledge acquired in the target task. Our experimental evidence gathered in known reinforcement learning benchmark tasks, as well as a challenging quadcopter to helicopter transfer task, suggests that prototype generation is feasible and, furthermore, that the filtering technique used is not as important as a correct transformation model.
机译：在机器学习中，学习任务很昂贵（需要许多训练样本），因此能够跨任务重用知识是人们普遍关注的问题。在空中机器人应用中就是这种情况，在这种情况下，自主的空中机器人无法与环境进行无害交互。原型生成是监督学习中常用的一种众所周知的技术，可以帮助减少学习任务所需的样本数量。但是，关于如何在强化学习任务中使用这些技术知之甚少。在这项工作中，我们提出了一种算法，该算法为了学习新的（目标）任务，首先基于先前在已知（源）任务中获取的样本生成新的样本原型。所提出的方法使用高斯过程来学习连续的多维转换函数，从而使该方法能够直接在连续（状态和动作）域中进行推理。我们基于从源任务中仔细选择样本子集的基础上生成原型（基于已知的过滤技术），并使用在目标任务中获得的（少量）知识对此类样本进行转换。我们在已知的强化学习基准任务以及具有挑战性的四轴直升机到直升机的转移任务中收集的实验证据表明，原型生成是可行的，此外，所使用的过滤技术不如正确的转换模型重要。

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