A Bayesian Rule for Adaptive Control based on Causal Interventions

DOI

10.2991/agi.2010.39How to use a DOI?

Keywords

Adaptive behavior, Intervention calculus, Bayesian control, Kullback-Leibler-divergence

Abstract

Explaining adaptive behavior is a central problem in artificial intelligence research. Here we formalize adaptive agents as mixture distributions over sequences of inputs and outputs (I/O). Each distribution of the mixture constitutes a "possible world", but the agent does not know which of the possible worlds it is actually facing. The problem is to adapt the I/O stream in a way that is compatible with the true world. A natural mea- sure of adaptation can be obtained by the Kullback Leibler (KL) divergence between the I/O distribution of the true world and the I/O distribution expected by the agent that is uncertain about possible worlds. In the case of pure input streams, the Bayesian mixture provides a well-known solution for this problem. We show, however, that in the case of I/O streams this solution breaks down, because outputs are issued by the agent itself and require a different probabilistic syntax as provided by intervention calculus. Based on this calculus, we obtain a Bayesian control rule that allows modeling adaptive behavior with mixture distributions over I/O streams. This rule might allow for a novel approach to adaptive control based on a minimum KL-principle.

Copyright

© 2010, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Pedro A. Ortega
AU  - Daniel A. Braun
PY  - 2010/06
DA  - 2010/06
TI  - A Bayesian Rule for Adaptive Control based on Causal Interventions
BT  - Proceedings of the 3d Conference on Artificial General Intelligence (2010)
PB  - Atlantis Press
SP  - 182
EP  - 187
SN  - 1951-6851
UR  - https://doi.org/10.2991/agi.2010.39
DO  - 10.2991/agi.2010.39
ID  - Ortega2010/06
ER  -