Branching Time Active Inference with Bayesian Filtering

Author:

Champion Théophile1,Grześ Marek2,Bowman Howard34

Affiliation:

1. University of Kent, School of Computing, Canterbury CT2 7NZ, U.K. TMAC3@KENT.AC.UK

2. University of Kent, School of Computing, Canterbury CT2 7NZ, U.K. M.GRZES@KENT.AC.UK

3. University of Birmingham, School of Psychology, Birmingham B15 2TT, U.K.

4. University of Kent, School of Computing, Canterbury CT2 7NZ, U.K. H.BOWMAN@KENT.AC.UK

Abstract

Abstract Branching time active inference is a framework proposing to look at planning as a form of Bayesian model expansion. Its root can be found in active inference, a neuroscientific framework widely used for brain modeling, as well as in Monte Carlo tree search, a method broadly applied in the reinforcement learning literature. Up to now, the inference of the latent variables was carried out by taking advantage of the flexibility offered by variational message passing, an iterative process that can be understood as sending messages along the edges of a factor graph. In this letter, we harness the efficiency of an alternative method for inference, Bayesian filtering, which does not require the iteration of the update equations until convergence of the variational free energy. Instead, this scheme alternates between two phases: integration of evidence and prediction of future states. Both phases can be performed efficiently, and this provides a forty times speedup over the state of the art.

Publisher

MIT Press

Subject

Cognitive Neuroscience,Arts and Humanities (miscellaneous)

Reference25 articles.

1. Finite-time analysis of the multiarmed bandit problem;Auer;Machine Learning,2002

2. Planning as inference;Botvinick;Trends in Cognitive Sciences,2012

3. A survey of Monte Carlo tree search methods;Browne;IEEE Transactions on Computational Intelligence and AI in Games,2012

4. Learning perception and planning with deep active inference;Çatal,2020

5. Branching time active inference: Empirical study and complexity class analysis;Champion;Neural Networks,2022

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