|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
Thermodynamics as a Theory of Decision-Making with Information Processing Costs
If you have a question about this talk, please contact Zoubin Ghahramani.
Perfectly rational decision-makers maximize expected utility, but crucially ignore the resource costs incurred when determining optimal actions. Here we propose an information-theoretic formalization of bounded rational decision-making where decision-makers trade off expected utility and information processing costs. As a result, the decision-making problem can be rephrased in terms of well-known 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 decision-makers. Furthermore, this framework allows rederiving a number of decision-making schemes including risk-sensitive and robust (minimax) decision-making 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 decision-making phenomena.
This talk is part of the Machine Learning @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsBAS Chemistry & Past Climate Seminars Medieval Archaeology Group Seminar Series Special Departmental Seminars
Other talks“The Impact of Impact: The future of science funding” PHANTOM: A Parallel Architecture for Practical Oblivious Computation Open Meeting : Upgrade of Linux desktops to SL6 Shaping neural circuits by early experience. Fair testing in Web 2.0 – where psychometricians’ and candidates’ interests meet TBC