• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Adaptive Behavior >Shifting Attention Using a Temporal Difference Prediction Error and High-Dimensional Input
【24h】

Shifting Attention Using a Temporal Difference Prediction Error and High-Dimensional Input

机译：使用时间差异预测误差和高维输入的转移注意力

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Research on reinforcement learning has increasingly focused on the role of neuromodulatory systems implicated in associative learning. Formulations of temporal difference (TD) learning have gained a great deal of attention due to the similarity of the TD prediction error and the observed activity of dopamine neurons in the primate midbrain. Recent work has attempted to integrate additional neuromodulatory systems such as noradrenaline and acetylcholine in a TD framework. Additional work has been done to remedy representational issues arising from TD variants that result in incorrect predictions of dopamine activity, as well as to incorporate the TD error signal in models of categorization. In this paper, an actor-critic model incorporating aspects of TD learning and psychological models of attention is described. The development of the model and the behavior of an autonomous agent in a simulated environment are examined and compared with a variant of TD learning lacking an attentional component. The agent learns to behave adaptively due to the shifting of attention to relevant aspects of a high-dimensional input. In contrast, the TD model exhibits perseverative behavior and comparatively slow learning in the same context. It is suggested that real-time models of attention may provide insight into neuromodulatory systems implicated in attention and representational learning.
机译：强化学习的研究越来越集中于联想学习中牵涉的神经调节系统的作用。由于TD预测误差的相似性以及在灵长类中脑中观察到的多巴胺神经元的活性，时差（TD）学习的公式引起了很多关注。最近的工作尝试将其他的神经调节系统（例如去甲肾上腺素和乙酰胆碱）整合到TD框架中。还进行了其他工作来纠正由TD变体引起的代表性问题，这些问题会导致对多巴胺活性的错误预测，以及将TD错误信号纳入分类模型。在本文中，描述了结合了TD学习和心理注意模型的行为者评论模型。研究了模型的开发和仿真环境中自治代理的行为，并将其与缺少注意力成分的TD学习的变体进行了比较。由于注意力转移到了高维输入的相关方面，代理学习了自适应行为。相反，TD模型在相同的环境中表现出持久的行为和相对缓慢的学习。建议注意的实时模型可以提供对涉及注意和代表性学习的神经调节系统的了解。

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