Feynman Lectures on Computation
Feynman Lectures on Computation
Time, space, and energy in reversible computing
Proceedings of the 2nd conference on Computing frontiers
A minimum relative entropy principle for learning and acting
Journal of Artificial Intelligence Research
Space-Time embedded intelligence
AGI'12 Proceedings of the 5th international conference on Artificial General Intelligence
| Hi-index | 0.00 |
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.