A conversion between utility and information
- 10.2991/agi.2010.10How to use a DOI?
- Behavior, Utility, Entropy, Information
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 infor- mation 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.
- © 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/).
Cite this article
TY - CONF AU - Pedro A. Ortega AU - Daniel A. Braun PY - 2010/06 DA - 2010/06 TI - A conversion between utility and information BT - Proceedings of the 3d Conference on Artificial General Intelligence (2010) PB - Atlantis Press SP - 47 EP - 52 SN - 1951-6851 UR - https://doi.org/10.2991/agi.2010.10 DO - 10.2991/agi.2010.10 ID - Ortega2010/06 ER -