Results 1  10
of
502
Minimax Value Iterarion Applied to Robotic Soccer
"... Abstract — These work focuses on constructing a dynamic programming algorithm to solve a class of Stochastic Games called twoperson zerosum games, inspired by the reinforcement learning algorithm MinimaxQ. In each state of the game, linear programming is used to find an Nash equilibrium, which ..."
Abstract
 Add to MetaCart
Abstract — These work focuses on constructing a dynamic programming algorithm to solve a class of Stochastic Games called twoperson zerosum games, inspired by the reinforcement learning algorithm MinimaxQ. In each state of the game, linear programming is used to find an Nash equilibrium, which
Minimax Value Iterarion Applied to Robotic Soccer
"... Abstract — This work focuses on developing a dynamic programming algorithm to solve a class of Stochastic Games called twoperson zerosum games, inspired by the reinforcement learning algorithm MinimaxQ. In each state of the game, linear programming is used to find a Nash equilibrium, which ensure ..."
Abstract
 Add to MetaCart
Abstract — This work focuses on developing a dynamic programming algorithm to solve a class of Stochastic Games called twoperson zerosum games, inspired by the reinforcement learning algorithm MinimaxQ. In each state of the game, linear programming is used to find a Nash equilibrium, which
Minimax
"... exact constant in supnorm for nonparametric regression with random design KARINE BERTIN∗ Abstract: We consider the nonparametric regression model with random design. We study the estimation of a regression function f in the uniform norm assuming that f belongs to a Hölder class. We determine the mi ..."
Abstract
 Add to MetaCart
the minimax exact constant and an asymptotically exact estimator. They depend on the minimum value of the design density. Key Words: nonparametric regression, minimax risk, minimax exact constant, uniform norm. AMS subject classification: 62G07, 62G20
Minimax
"... exact constant in supnorm for nonparametric regression with random design KARINE BERTIN∗ Abstract: We consider the nonparametric regression model with random design. We study the estimation of a regression function f in the uniform norm assuming that f belongs to a Hölder class. We determine the mi ..."
Abstract
 Add to MetaCart
the minimax exact constant and an asymptotically exact estimator. They depend on the minimum value of the design density. Key Words: nonparametric regression, minimax risk, minimax exact constant, uniform norm. AMS subject classification: 62G07, 62G20
Wedgelets: nearlyminimax estimation of edges
 Ann. Statist
, 1999
"... We study a simple “Horizon Model ” for the problem of recovering an image from noisy data; in this model the image has an edge with αHölder regularity. Adopting the viewpoint of computational harmonic analysis, we develop an overcomplete collection of atoms called wedgelets, dyadically organized in ..."
Abstract

Cited by 113 (8 self)
 Add to MetaCart
indicator functions with a variety of locations, scales, and orientations. The wedgelet representation provides nearlyoptimal representations of objects in the Horizon model, as measured by minimax description length. We show how to rapidly compute a wedgelet approximation to noisy data by finding a
Is RealValued Minimax Pathological?
"... Deeper searches in gameplaying programs relying on the minimax principle generally produce better results. Theoretical analyses, however, suggest that in many cases minimaxing amplifies the noise introduced by the heuristic function used to evaluate the leaves of the game tree, leading to what is k ..."
Abstract

Cited by 8 (2 self)
 Add to MetaCart
is known as pathological behavior, where deeper searches produce worse results. In most minimax models analyzed in previous research, positions ’ true values and sometimes also heuristic values were only losses and wins. In contrast to this, a model is proposed in this paper that uses real numbers for both
Minimax and the Value of Information∗
, 2014
"... In his discussion of minimax decision rules, Savage (1954, p. 170) presents an example purporting to show that minimax applied to negative expected utility (referred to by Savage as “negative income”) is an inadequate decision criterion for statistics; he suggests the application of a minimax regre ..."
Abstract
 Add to MetaCart
that a minimax regret agent would never pay a positive cost to observe. On closer inspection, I find that minimax regret is more resilient to this critique than would first appear. In particular, there are cases in which no experiment has any value to an agent employing the minimax negative income rule
Minimax Theorems for VectorValued
"... We present a Ky Fan type inequality of mixed kind for vectorvalued multifunctions. We use it for proving our first type minimax theorem for vectorvalued multifunctions. It is a generalization of the classical Sion minimax theorem for scalar functions (in the compact case), as well as, a generaliza ..."
Abstract
 Add to MetaCart
We present a Ky Fan type inequality of mixed kind for vectorvalued multifunctions. We use it for proving our first type minimax theorem for vectorvalued multifunctions. It is a generalization of the classical Sion minimax theorem for scalar functions (in the compact case), as well as, a
Minimax Embeddings
 In Advances in Neural Information Processing Systems
, 2004
"... Spectral methods for nonlinear dimensionality reduction (NLDR) impose a neighborhood graph on point data and compute eigenfunctions of a quadratic form generated from the graph. We introduce a more general and more robust formulation of NLDR based on the singular value decomposition (SVD). In this f ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Spectral methods for nonlinear dimensionality reduction (NLDR) impose a neighborhood graph on point data and compute eigenfunctions of a quadratic form generated from the graph. We introduce a more general and more robust formulation of NLDR based on the singular value decomposition (SVD
Econometric Applications of Minimax . . .
, 1999
"... Gilboa and Schmeidler (1989) provide axioms on preferences that imply a set of distributions and a preference ordering based on the minimum expected utility with respect to this set. We consider joint distributions for data and for the random variables that, together with the agent's choice, de ..."
Abstract
 Add to MetaCart
given prior and then solving a concave program to find the leastfavorable prior distribution. The minimax value we obtain for the finite set of priors is a lower bound on the minimax risk for a larger set, such as the in nite set that includes all point masses on a Euclidean space, as in Wald (1950
Results 1  10
of
502