Complexity of Solving Decision Trees with Skew-Symmetric Bilinear Utility
نویسندگان
چکیده
We study the complexity of solving decision trees with a Skew-Symmetric Bilinear (SSB) utility function. The SSB model is an extension of Expected Utility (EU) with enhanced descriptive possibilities. Unlike EU, the optimality principle does not hold for SSB, which makes its optimization trickier. We show that determining an SSB optimal plan is NP-hard if one only considers deterministic plans while it is polynomial time if one allows randomized plans. With the Weighted EU model (a special case of SSB), the problem becomes polynomial in both settings. Our numerical tests show the operationality of the methods.
منابع مشابه
Solving MDPs with Skew Symmetric Bilinear Utility Functions
In this paper we adopt Skew Symmetric Bilinear (SSB) utility functions to compare policies in Markov Decision Processes (MDPs). By considering pairs of alternatives, SSB utility theory generalizes von Neumann and Morgenstern’s expected utility (EU) theory to encompass rational decision behaviors that EU cannot accommodate. We provide a game-theoretic analysis of the problem of identifying an SS...
متن کاملModel-Free Reinforcement Learning with Skew-Symmetric Bilinear Utilities
In reinforcement learning, policies are typically evaluated according to the expectation of cumulated rewards. Researchers in decision theory have argued that more sophisticated decision criteria can better model the preferences of a decision maker. In particular, Skew-Symmetric Bilinear (SSB) utility functions generalize von Neumann and Morgenstern’s expected utility (EU) theory to encompass r...
متن کاملFast Structured Matrix Computations: Tensor Rank and Cohn-Umans Method
We discuss a generalization of the Cohn–Umans method, a potent technique developed for studying the bilinear complexity of matrix multiplication by embedding matrices into an appropriate group algebra. We investigate how the Cohn–Umans method may be used for bilinear operations other than matrix multiplication, with algebras other than group algebras, and we relate it to Strassen’s tensor rank ...
متن کاملAxiomatization of a Preference for Most Probable Winner
1 L to lottery 2 L when the probability that 1 L delivers a better outcome than 2 L is higher than the probability that 2 L delivers a better outcome than 1 L . Such a preference can be rationalized by three standard axioms (completeness, continuity and first order stochastic dominance) and two less standard ones (weak independence and a fanning-in). A preference for the most probable winner ca...
متن کاملTesting the Predictions of Decision Theories in a Natural Experiment When Half a Million Is at Stake
In the television show Affari Tuoi an individual faces a sequence of binary choices between a risky lottery with equiprobable prizes of up to half a million euros and a monetary amount for certain. The decisions of 114 show participants are used to test the predictions of ten decision theories: risk neutrality, expected utility theory, fanning-out hypothesis (weighted utility theory, transitive...
متن کامل