A Minimum Relative Entropy Principle for Learning and Acting

Details A Minimum Relative Entropy Principle for Learning and Acting A Minimum Relative Entropy Principle for Learning and Acting

2008-10-20

arxiv.org/abs/0810.3605v3

Computer Science

Artificial Intelligence

36 pages, 11 figures

Scientific paper

This paper proposes a method to construct an adaptive agent that is universal with respect to a given class of experts, where each expert is an agent that has been designed specifically for a particular environment. This adaptive control problem is formalized as the problem of minimizing the relative entropy of the adaptive agent from the expert that is most suitable for the unknown environment. If the agent is a passive observer, then the optimal solution is the well-known Bayesian predictor. However, if the agent is active, then its past actions need to be treated as causal interventions on the I/O stream rather than normal probability conditions. Here it is shown that the solution to this new variational problem is given by a stochastic controller called the Bayesian control rule, which implements adaptive behavior as a mixture of experts. Furthermore, it is shown that under mild assumptions, the Bayesian control rule converges to the control law of the most suitable expert.

Affiliated with

Also associated with

No associations

Rating

A Minimum Relative Entropy Principle for Learning and Acting does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A Minimum Relative Entropy Principle for Learning and Acting, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Minimum Relative Entropy Principle for Learning and Acting will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-266299