Computer Science – Artificial Intelligence
Scientific paper
2009-11-26
AGI-2010
Computer Science
Artificial Intelligence
AGI-2010. 6 pages, 1 figure
Scientific paper
Rewards typically express desirabilities or preferences over a set of alternatives. Here we propose that rewards can be defined for any probability distribution based on three desiderata, namely that rewards should be real-valued, additive and order-preserving, where the latter implies that more probable events should also be more desirable. Our main result states that rewards are then uniquely determined by the negative information content. To analyze stochastic processes, we define the utility of a realization as its reward rate. Under this interpretation, we show that the expected utility of a stochastic process is its negative entropy rate. Furthermore, we apply our results to analyze agent-environment interactions. We show that the expected utility that will actually be achieved by the agent is given by the negative cross-entropy from the input-output (I/O) distribution of the coupled interaction system and the agent's I/O distribution. Thus, our results allow for an information-theoretic interpretation of the notion of utility and the characterization of agent-environment interactions in terms of entropy dynamics.
Braun Daniel A.
Ortega Pedro A.
No associations
LandOfFree
A conversion between utility and information 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 conversion between utility and information, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A conversion between utility and information will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-116868