arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1503.04187cs.AI
收藏

一种最小主动推理Agent

A Minimal Active Inference Agent

University of Sussex(萨塞克斯大学)

Simon McGregor, Manuel Baltieri, Christopher L. Buckley

摘要:

认知神经科学中所谓的“自由能原理”(FEP)的研究正变得越来越引人注目。到目前为止,对这个理论的介绍已经证明对许多读者来说很难理解,但它主要依赖于两个相对简单的想法:首先,规范或目的论的值可以表示为概率分布(主动推理),其次,近似贝叶斯推理可以通过模型参数的梯度下降有效地执行(自由能原理)。主动推理的概念对于包括认知科学和人工智能以及认知神经科学在内的许多学科都具有极大的兴趣,并且值得更广泛地了解。本文试图为来自不同科学背景的读者提供一个对主动推理和信息自由能的可访问的介绍。在这项工作中,介绍了一个基于代理的模型与代理试图预测其位置在一个一维的离散世界使用的方法从FEP。

英文摘要:

Research on the so-called "free-energy principle'' (FEP) in cognitive neuroscience is becoming increasingly high-profile. To date, introductions to this theory have proved difficult for many readers to follow, but it depends mainly upon two relatively simple ideas: firstly that normative or teleological values can be expressed as probability distributions (active inference), and secondly that approximate Bayesian reasoning can be effectively performed by gradient descent on model parameters (the free-energy principle). The notion of active inference is of great interest for a number of disciplines including cognitive science and artificial intelligence, as well as cognitive neuroscience, and deserves to be more widely known. This paper attempts to provide an accessible introduction to active inference and informational free-energy, for readers from a range of scientific backgrounds. In this work introduce an agent-based model with an agent trying to make predictions about its position in a one-dimensional discretized world using methods from the FEP.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑