...
首页> 外文期刊>Adaptive Behavior >Encouraging reactivity to create robust machines
【24h】

Encouraging reactivity to create robust machines

机译:鼓励反应性来创建强大的机器

获取原文
获取原文并翻译 | 示例
           

摘要

The robustness of animal behavior is unmatched by current machines, which often falter when exposed to unforeseen conditions. While animals are notably reactive to changes in their environment, machines often follow finely tuned yet inflexible plans. Thus, instead of the traditional approach of training such machines over many different unpredictable scenarios in detailed simulations (which is the most intuitive approach to inducing robustness), this work proposes to train machines to be reactive to their environment. The idea is that robustness may result not from detailed internal models or finely tuned control policies but from cautious exploratory behavior. Supporting this hypothesis, robots trained to navigate mazes with a reactive disposition prove more robust than those trained over many trials yet not rewarded for reactive behavior in both simulated tests and when embodied in real robots. The conclusion is that robustness may neither require an accurate model nor finely calibrated behavior.
机译:当前的机器无法比拟动物行为的鲁棒性,当暴露于不可预见的条件下时,机器通常会动摇。尽管动物对周围环境的变化具有显着的反应能力,但机器通常遵循经过微调但又不灵活的计划。因此,代替在详细的模拟中在许多不同的不可预测的情况下训练此类机器的传统方法(这是诱导鲁棒性的最直观的方法),该工作建议训练机器使其对环境具有反应性。这个想法是,鲁棒性可能不是由详细的内部模型或经过微调的控制策略引起的,而是由谨慎的探索行为引起的。支持该假设的事实是,受过反应性配置的迷宫导航的机器人比经过许多试验而受过训练的机器人更强大,但无论是在模拟测试中还是体现在真实机器人中,都没有因反应而获得奖励。结论是,鲁棒性可能既不需要精确的模型也不需要精细的校准行为。

著录项

  • 来源
    《Adaptive Behavior》 |2013年第6期|484-500|共17页
  • 作者单位

    The University of Texas at Austin, 2400 Inner Campus Drive , Austin, TX 78712, US;

    Cornell University, Ithaca, NY, USA;

    Space and Naval Warfare Systems Center Pacic, San Diego, CA, USA;

    University of Central Florida, Orlando, FL, USA;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

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