Active Inference or Control as Inference? A Unifying View

10/01/2020
by   Joe Watson, et al.
6

Active inference (AI) is a persuasive theoretical framework from computational neuroscience that seeks to describe action and perception as inference-based computation. However, this framework has yet to provide practical sensorimotor control algorithms that are competitive with alternative approaches. In this work, we frame active inference through the lens of control as inference (CaI), a body of work that presents trajectory optimization as inference. From the wider view of `probabilistic numerics', CaI offers principled, numerically robust optimal control solvers that provide uncertainty quantification, and can scale to nonlinear problems with approximate inference. We show that AI may be framed as partially-observed CaI when the cost function is defined specifically in the observation states.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/07/2019

Stochastic Optimal Control as Approximate Input Inference

Optimal control of stochastic nonlinear dynamical systems is a major cha...
research
08/22/2022

Deriving time-averaged active inference from control principles

Active inference offers a principled account of behavior as minimizing a...
research
05/22/2018

Active Inference for Adaptive BCI: application to the P300 Speller

Adaptive Brain-Computer interfaces (BCIs) have shown to improve performa...
research
08/18/2022

Mapping Husserlian phenomenology onto active inference

Phenomenology is the rigorous descriptive study of conscious experience....
research
05/17/2021

Stochastic Control through Approximate Bayesian Input Inference

Optimal control under uncertainty is a prevailing challenge in control, ...
research
05/12/2020

Active Inference for Integrated State-Estimation, Control, and Learning

This work presents an approach for control, state-estimation and learnin...
research
03/10/2021

Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk

Discrete-time stochastic optimal control remains a challenging problem f...

Please sign up or login with your details

Forgot password? Click here to reset