Whence the Expected Free Energy?

Author:

Millidge Beren1,Tschantz Alexander2,Buckley Christopher L.3

Affiliation:

1. School of Informatics, University of Edinburgh, Edinburgh, EH8 9AB, U.K. beren@millidge.name

2. Sackler Center for Consciousness Science, School of Engineering and Informatics, University of Sussex, Falmer, Brighton, BN1 9RH, U.K. tschantz.alec@gmail.com

3. Evolutionary and Adaptive Systems Research Group, School of Engineering and Informatics, University of Sussex, Falmer, Brighton, BN1 9RH, U.K. C.L.Buckley@sussex.ac.uk

Abstract

Abstract The expected free energy (EFE) is a central quantity in the theory of active inference. It is the quantity that all active inference agents are mandated to minimize through action, and its decomposition into extrinsic and intrinsic value terms is key to the balance of exploration and exploitation that active inference agents evince. Despite its importance, the mathematical origins of this quantity and its relation to the variational free energy (VFE) remain unclear. In this letter, we investigate the origins of the EFE in detail and show that it is not simply ”the free energy in the future.” We present a functional that we argue is the natural extension of the VFE but actively discourages exploratory behavior, thus demonstrating that exploration does not directly follow from free energy minimization into the future. We then develop a novel objective, the free energy of the expected future (FEEF), which possesses both the epistemic component of the EFE and an intuitive mathematical grounding as the divergence between predicted and desired futures.

Publisher

MIT Press - Journals

Subject

Cognitive Neuroscience,Arts and Humanities (miscellaneous)

Reference83 articles.

1. Attias, H. (2003). Planning by probabilistic inference. In Proceedings of the 9th International Workshop on Artificial Intelligence and Statistics.

2. Baldi, P., & Itti, L. (2010). Of bits and wows: A Bayesian theory of surprise with applications to attention. Neural Networks, 23(5), 649–666.

3. Baltieri, M., & Buckley, C. L. (2017). An active inference implementation of phototaxis. In Proceedings of the Artificial Life Conference (pp. 36–43). Berlin: Spring-Verlag.

4. Baltieri, M., & Buckley, C. L. (2018). A probabilistic interpretation of PID controllers using active inference. In From Animals to Animats: Proceedings of the International Conference on Simulation of Adaptive Behavior (pp. 15–26). Cambridge, MA: MIT Press.

5. Bastos, A. M., Usrey, W. M., Adams, R. A., Mangun, G. R., Fries, P., & Friston, K. J. (2012). Canonical microcircuits for predictive coding. Neuron, 76(4), 695–711.

Cited by 35 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3