Learning and Exploitation Do Not Conflict Under Minimax Optimality
نویسنده
چکیده
\Ve show thaI, H.daptive n�al time dyrmmic prograrnming ex tended with the action selection strategy which chooses the best action Recording 1.0 the laLest, estimaLe orLhf' cos!' rllndiofl yields i-\..'i.yrnptoLicl-tlly 0pLirnal poli(:ies within riniLe Limp lJnder· !,lIP minimax 0pLirnality criu-' rian. H'om this it follows that learning and exploitation do not confiict under this special optimality criterion. We relate this result to learning optimal strategies in repeated two-player zero-sum deterministic games.
منابع مشابه
On the Minimax Optimality of Block Thresholded Wavelets Estimators for ?-Mixing Process
We propose a wavelet based regression function estimator for the estimation of the regression function for a sequence of ?-missing random variables with a common one-dimensional probability density function. Some asymptotic properties of the proposed estimator based on block thresholding are investigated. It is found that the estimators achieve optimal minimax convergence rates over large class...
متن کاملOptimality Conditions for Minimax Programming of Analytic Functions
In this paper, we investigate a minimax complex programming problem. Several sufficient Optimality conditions are established under the framework of generalized convexity for analytic functions. Employing the sufficient optimality conditions, we have proved the weak, strong and strict converse duality theorems for the complex minimax programming problem.
متن کاملTruncated Linear Minimax Estimator of a Power of the Scale Parameter in a Lower- Bounded Parameter Space
Minimax estimation problems with restricted parameter space reached increasing interest within the last two decades Some authors derived minimax and admissible estimators of bounded parameters under squared error loss and scale invariant squared error loss In some truncated estimation problems the most natural estimator to be considered is the truncated version of a classic...
متن کاملAsymptotic Optimality of Empirical Likelihood for Selecting Moment Restrictions
This paper proposes large deviation optimal properties of the empirical likelihood testing (ELT) moment selection procedures for moment restriction models. Since the parameter spaces of the moment selection problem is discrete, the conventional Pitman-type local alternative approach is not very helpful. By applying the theory of large deviations, we analyze convergence rates of the error probab...
متن کاملLearning sub-Gaussian classes : Upper and minimax bounds
Most the results contained in this note have been presented at the SMF meeting, which took place in May 2011; the rest have been obtained shortly after the time of the meeting. The question we study has to do with the optimality of Empirical Risk Minimization as a learning procedure in a convex class – when the problem is subgaussian. Subgaussian learning problems are a natural object because t...
متن کامل