首页> 美国卫生研究院文献>Frontiers in Computational Neuroscience >Learned graphical models for probabilistic planning provide a new class of movement primitives
【2h】

Learned graphical models for probabilistic planning provide a new class of movement primitives

机译:学习的概率规划图形模型提供了新的运动原语类

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

Biological movement generation combines three interesting aspects: its modular organization in movement primitives (MPs), its characteristics of stochastic optimality under perturbations, and its efficiency in terms of learning. A common approach to motor skill learning is to endow the primitives with dynamical systems. Here, the parameters of the primitive indirectly define the shape of a reference trajectory. We propose an alternative MP representation based on probabilistic inference in learned graphical models with new and interesting properties that complies with salient features of biological movement control. Instead of endowing the primitives with dynamical systems, we propose to endow MPs with an intrinsic probabilistic planning system, integrating the power of stochastic optimal control (SOC) methods within a MP. The parameterization of the primitive is a graphical model that represents the dynamics and intrinsic cost function such that inference in this graphical model yields the control policy. We parameterize the intrinsic cost function using task-relevant features, such as the importance of passing through certain via-points. The system dynamics as well as intrinsic cost function parameters are learned in a reinforcement learning (RL) setting. We evaluate our approach on a complex 4-link balancing task. Our experiments show that our movement representation facilitates learning significantly and leads to better generalization to new task settings without re-learning.
机译:生物运动的产生结合了三个有趣的方面:​​其在运动原语(MP)中的模块化组织,其在扰动下的随机最优特征以及在学习方面的效率。运动技能学习的一种常用方法是赋予原语动力系统。在此,图元的参数间接定义了参考轨迹的形状。我们提出了基于概率推理的学习图形模型的另一种MP表示形式,该模型具有新颖有趣的特性,符合生物运动控制的显着特征。与其给原语赋予动态系统,不如给MP赋予内在的概率规划系统,将MP中的随机最优控制(SOC)方法的功能整合在一起。原语的参数化是一个表示动力学和内在成本函数的图形模型,因此在该图形模型中的推断会产生控制策略。我们使用与任务相关的功能(例如,通过某些通孔的重要性)对固有成本函数进行参数化。在强化学习(RL)设置中学习系统动力学以及固有成本函数参数。我们评估我们在复杂的4链路平衡任务上的方法。我们的实验表明,我们的运动表示形式极大地促进了学习,并且无需重新学习就可以更好地将其推广到新的任务设置。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

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