...
首页> 外文期刊>電子情報通信学会技術研究報告. ニュ-ロコンピュ-ティング. Neurocomputing >A model of prism adaptation based on reinforcement learning and supervised learning
【24h】

A model of prism adaptation based on reinforcement learning and supervised learning

机译:基于强化学习和监督学习的棱镜适应模型

获取原文
获取原文并翻译 | 示例
           

摘要

The authors propose a visuo-motor learning model based on reinforcement learning (RL) and supervised learning (SL), in order to explain the human behavior during prism adaptation. In the proposed model, the motor planning module, which works with RL, chooses appropriate motor commands basted on the prediction by the internal model modules which work with SL. Moreover, an appropriate internal model is selected by the RL-based context switching module. Utilizing the "reliability of internal model," the model realizes both parameter modification for a gradual environmental change and context-switch for a sudden environmental change. The behavior of the proposed model is illustrated through a computer simulation. The relation between the proposed model and other modular learning algorithms is discussed.
机译:作者提出了一种基于强化学习(RL)和监督学习(SL)的视觉运动学习模型,以解释棱镜适应过程中的人类行为。在提出的模型中,与RL配合使用的电机计划模块根据与SL配合使用的内部模型模块的预测选择适当的电机命令。此外,基于RL的上下文切换模块选择了适当的内部模型。利用“内部模型的可靠性”,该模型既可以实现针对逐渐的环境变化的参数修改,也可以实现针对突然的环境变化的上下文切换。通过计算机仿真说明了所提出模型的行为。讨论了所提出的模型与其他模块化学习算法之间的关系。

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