Computer Science – Artificial Intelligence
Scientific paper
2011-07-28
The Fourth Conference on General Artificial Intelligence (AGI-11), 2011
Computer Science
Artificial Intelligence
10 pages. The original publication is available at www.springerlink.com
Scientific paper
Perfectly rational decision-makers maximize expected utility, but crucially ignore the resource costs incurred when determining optimal actions. Here we employ an axiomatic framework for bounded rational decision-making based on a thermodynamic interpretation of resource costs as information costs. This leads to a variational "free utility" principle akin to thermodynamical free energy that trades off utility and information costs. We show that bounded optimal control solutions can be derived from this variational principle, which leads in general to stochastic policies. Furthermore, we show that risk-sensitive and robust (minimax) control schemes fall out naturally from this framework if the environment is considered as a bounded rational and perfectly rational opponent, respectively. When resource costs are ignored, the maximum expected utility principle is recovered.
Braun Daniel A.
Ortega Pedro A.
No associations
LandOfFree
Information, Utility & Bounded Rationality 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 Information, Utility & Bounded Rationality, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Information, Utility & Bounded Rationality will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-415052