学习身体启示,简化行动空间
Learning body-affordances to simplify action spaces
摘要:
控制具有许多致动自由度的具体代理是一项具有挑战性的任务。我们提出了一种方法,可以发现和上下文相关的高层次的行动或身体启示之间的插值。这些提供了一个抽象的,低维的接口索引高维和时间扩展的动作策略。我们的方法与机器学习文献中的最新方法有关,但在概念上更简单,更容易实现。更具体地说,我们的方法需要选择一个n维的目标传感器空间,赋予距离度量。然后,该方法学习在整个目标传感器空间中尽可能远地传播的可能反应性身体示能表示的也n维嵌入。
英文摘要:
Controlling embodied agents with many actuated degrees of freedom is a challenging task. We propose a method that can discover and interpolate between context dependent high-level actions or body-affordances. These provide an abstract, low-dimensional interface indexing high-dimensional and time- extended action policies. Our method is related to recent ap- proaches in the machine learning literature but is conceptually simpler and easier to implement. More specifically our method requires the choice of a n-dimensional target sensor space that is endowed with a distance metric. The method then learns an also n-dimensional embedding of possibly reactive body-affordances that spread as far as possible throughout the target sensor space.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。