首页> 外文会议>International conference on the simulation and synthesis of living systems >Common Concepts in Agent Groups, Symmetries, and Conformity in a Simple Environment
【24h】

Common Concepts in Agent Groups, Symmetries, and Conformity in a Simple Environment

机译:简单环境中的座席组,对称性和整合性中的常用概念

获取原文

摘要

We analyze representations of the world attained through an infomax principle by agents acting in a simple environment. The representations obtained by different agents in general differ to some extent from each other in different instances. This gives rise to ambiguities in how the environment is represented by the different agents. We now develop an information-theoretic formalism able to extract a 'common conceptualization' of the world for a group of agents. It turns out that the common conceptualization intuitively seems to capture much higher regularities or symmetries of the environment than the individual representations.We formalize the notion of identifying symmetries in the environment - with respect to 'extrinsic' operations on the environment as well as with respect to 'intrinsic' operations, i.e. the reconfiguration of the agent's embodiment. In particular, using the latter formalism, we can re-wire an agent to conform to the highly symmetric common conceptualization to a much higher degree than an unrefined agent; and that without having to re-optimize the agent from scratch. In other words, we can 're-educate' an agent to conform to the de-individualized 'concept' of the agent group with comparatively little effort.
机译:我们分析了在简单环境中行动的代理通过infomax原理获得的世界表示。通常,在不同情况下,由不同代理获得的表示形式在某种程度上彼此不同。这引起了环境如何由不同代理人表示的歧义。现在,我们开发了一种信息理论形式主义,能够为一组特工提取世界的“共同概念化”。事实证明,普通的概念化似乎比单个表示法直观地捕获了更高的环境规律性或对称性。我们对识别环境中对称性的概念进行了形式化-相对于对环境的“外部”操作“内部”操作,即重新配置代理的实施例。特别是,使用后一种形式主义,我们可以重新连接一个代理以使其与高度对称的通用概念化相一致,其程度要比未改进的代理更高。而且无需从头开始重新优化代理。换句话说,我们可以用较少的精力“重新教育”一个代理以使其符合该代理组的去个体化的“概念”。

著录项

  • 来源
  • 会议地点 Winchester(GB)
  • 作者

    Marco Moeller; Daniel Polani;

  • 作者单位

    Theory of Complex Systems Group Institute of Solid State Physics Technical University of Darmstadt Germany Adaptive Systems Group School of Computer Science University of Hertfordshire UK;

    Adaptive Systems Group School of Computer Science University of Hertfordshire UK;

  • 会议组织
  • 原文格式 PDF
  • 正文语种
  • 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