Möller Marco, Polani Daniel
Theory of Complex Systems Group, Institute of Solid State Physics, Technical University of Darmstadt, Germany.
Adaptive Systems Research Group, Department of Computer Science, University of Hertfordshire, Hatfield, UK.
Interface Focus. 2023 Apr 14;13(3):20230006. doi: 10.1098/rsfs.2023.0006. eCollection 2023 Jun 6.
The paper studies principles behind structured, especially symmetric, representations through enforced inter-agent conformity. For this, we consider agents in a simple environment who extract individual representations of this environment through an information maximization principle. The representations obtained by different agents differ in general to some extent from each other. This gives rise to ambiguities in how the environment is represented by the different agents. Using a variant of the information bottleneck principle, we extract a 'common conceptualization' of the world for this group of agents. It turns out that the common conceptualization appears to capture much higher regularities or symmetries of the environment than the individual representations. We further formalize the notion of identifying symmetries in the environment both with respect to 'extrinsic' (birds-eye) operations on the environment as well as with respect to 'intrinsic' operations, i.e. subjective operations corresponding to the reconfiguration of the agent's embodiment. Remarkably, using the latter formalism, one 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, one can 're-educate' an agent to conform to the de-individualized 'concept' of the agent group with comparatively little effort.
本文研究了通过强制智能体之间的一致性来实现结构化(尤其是对称)表示的原理。为此,我们考虑处于简单环境中的智能体,它们通过信息最大化原理提取该环境的个体表示。不同智能体获得的表示通常在某种程度上彼此不同。这就导致了不同智能体对环境的表示方式存在模糊性。我们使用信息瓶颈原理的一个变体,为这组智能体提取出世界的“共同概念化”。结果表明,与个体表示相比,共同概念化似乎捕捉到了环境中更高的规律性或对称性。我们进一步形式化了在环境中识别对称性的概念,既涉及对环境的“外在”(鸟瞰)操作,也涉及“内在”操作,即与智能体自身形态重新配置相对应的主观操作。值得注意的是,使用后一种形式主义,与未经过优化的智能体相比,人们可以将一个智能体重连,使其在更高程度上符合高度对称的共同概念化;而且,无需从头重新优化智能体。换句话说,人们可以相对轻松地“重新训练”一个智能体,使其符合智能体群体的去个性化“概念”。