Thermodynamics as a Theory of DecisionMaking with Information Processing Costs
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Zoubin Ghahramani.
Perfectly rational decisionmakers maximize expected utility, but crucially ignore the resource costs incurred when determining optimal actions. Here we propose an informationtheoretic formalization of bounded rational decisionmaking where decisionmakers trade off expected utility and information processing costs. As a result, the decisionmaking problem can be rephrased in terms of wellknown concepts from thermodynamics and statistical physics, such that the same exponential family distributions that govern statistical ensembles can be used to describe the stochastic choice behavior of bounded decisionmakers. Furthermore, this framework allows rederiving a number of decisionmaking schemes including risksensitive and robust (minimax) decisionmaking as well as more recent approximately optimal schemes that are based on the relative entropy. In the limit when resource costs are ignored, the maximum expected utility principle is recovered. Since most of the mathematical machinery can be borrowed from statistical physics, the main contribution is to show how a thermodynamic model of bounded rationality can provide a unified view of diverse decisionmaking phenomena.
This talk is part of the Machine Learning @ CUED series.
This talk is included in these lists:
Note that exdirectory lists are not shown.
