首页> 外国专利> SOLVING BASED INTROSPECTION TO AUGMENT THE TRAINING OF REINFORCEMENT LEARNING AGENTS FOR CONTROL AND PLANNING ON ROBOTS AND AUTONOMOUS VEHICLES

SOLVING BASED INTROSPECTION TO AUGMENT THE TRAINING OF REINFORCEMENT LEARNING AGENTS FOR CONTROL AND PLANNING ON ROBOTS AND AUTONOMOUS VEHICLES

机译:基于解决方案的内向型增强对机器人和自主车辆的控制和计划的强化学习代理的培训

摘要

Described is a system for controlling a mobile platform. A neural network that runs on the mobile platform is trained based on a current state of the mobile platform. A Satisfiability Modulo Theories (SMT) solver capable of reasoning over non-linear activation functions is periodically queried to obtain examples of states satisfying specified constraints of the mobile platform. The neural network is then trained on the examples of states. Following training on the examples of states, the neural network selects an action to be performed by the mobile platform in its environment. Finally, the system causes the mobile platform to perform the selected action in its environment.
机译:描述了一种用于控制移动平台的系统。基于移动平台的当前状态来训练在移动平台上运行的神经网络。周期性地查询能够对非线性激活函数进行推理的可满足性模理论(SMT)求解器,以获得满足移动平台指定约束的状态示例。然后在状态示例中训练神经网络。在对状态示例进行训练之后,神经网络选择移动平台在其环境中要执行的动作。最后,系统使移动平台在其环境中执行选定的操作。

著录项

  • 公开/公告号WO2020149940A1

    专利类型

  • 公开/公告日2020-07-23

    原文格式PDF

  • 申请/专利权人 HRL LABORATORIES LLC;

    申请/专利号WO2019US62699

  • 发明设计人 WARREN MICHAEL A.;SERRANO CHRISTOPHER;

    申请日2019-11-21

  • 分类号G06N3/08;G06N5;G06N3;G06N3/04;

  • 国家 WO

  • 入库时间 2022-08-21 11:10:10

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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