Does Empowerment Maximisation Allow for Enactive Artificial Agents?

Does Empowerment Maximisation Allow for Enactive Artificial Agents?
复制标题

赋权最大化是否允许活跃的人工代理?

DOI:
--
复制
发表时间:
2016
期刊:
IEEE Symposium on Artificial Life
影响因子:
--
通讯作者:
Christoph Salge
Christoph Salge
中科院分区:
--
文献类型:
--
作者:
C. Guckelsberger;Christoph Salge

文献摘要

参考文献

被引文献

相似文献

生成式人工智能框架希望通过借鉴生成认知科学的生物系统基础,克服具身人工智能在意义构建方面的局限性。具身人工智能试图将意义建立在感觉运动交互的基础上,而生成式人工智能通过将感觉运动交互建立在自主能动性的基础上,增加了更多要求。这种转变的核心是对真正内在价值函数的需求。我们认为,赋权(一种基于智能体具身性的信息理论量)代表了这样一种函数。我们详细强调了赋权最大化在满足生成式人工智能要求(即建立构成性自主性和适应性)方面的作用。然后我们认为,基于不稳定存在的赋权使智能体能够根据环境特征与其自身身份的相关性构建一个世界。
The enactive AI framework wants to overcome the sense-making limitations of embodied AI by drawing on the bio-systemic foundations of enactive cognitive science. While embodied AI tries to ground meaning in sensorimotor interaction, enactive AI adds further requirements by grounding sensorimotor interaction in autonomous agency. At the core of this shift is the requirement for a truly intrinsic value function. We suggest that empowerment, an information-theoretic quantity based on an agents embodiment, represents such a function. We highlight the role of empowerment maximisation in satisfying the requirements of enactive AI, i.e. establishing constitutive autonomy and adaptivity, in detail. We then argue that empowerment, grounded in a precarious existence, allows an agent to enact a world based on the relevance of environmental features in respect to its own identity.
DOI: 10.3390/e16063357
发表时间: 2014
期刊: Entropy
影响因子: 2.7
作者:
Guckelsberger C
通讯作者: Guckelsberger C
DOI: 10.1037/0022-3514.54.5.768
发表时间: 1988-05-01
影响因子: 7.6
作者:
STRACK, F;MARTIN, LL;STEPPER, S
通讯作者: STEPPER, S