Help Privacy Policy Disclaimer
  Advanced SearchBrowse




Conference Paper

A Bayesian rule for adaptive control based on causal interventions

There are no MPG-Authors in the publication available
External Resource
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available

Ortega, P., & Braun, D. (2010). A Bayesian rule for adaptive control based on causal interventions. In E. Hutter, & M. Kitzelmann (Eds.), Third Conference on Artificial General Intelligence (AGI 2010) (pp. 121-126). Amsterdam, Netherlands: Atlantis Press.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0013-C102-A
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 measure 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.