Sciweavers

31 search results - page 2 / 7
» Sampled fictitious play for approximate dynamic programming
Sort
View
STOC
2003
ACM
164views Algorithms» more  STOC 2003»
16 years 1 months ago
Approximate counting by dynamic programming
We give efficient algorithms to sample uniformly, and count approximately, the solutions to a zero-one knapsack problem. The algorithm is based on using dynamic programming to pro...
Martin E. Dyer
ICML
2010
IEEE
15 years 2 months ago
Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes
Approximate dynamic programming has been used successfully in a large variety of domains, but it relies on a small set of provided approximation features to calculate solutions re...
Marek Petrik, Gavin Taylor, Ronald Parr, Shlomo Zi...
ATAL
2005
Springer
15 years 7 months ago
Improving reinforcement learning function approximators via neuroevolution
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Shimon Whiteson
ATAL
2010
Springer
15 years 2 months ago
History-dependent graphical multiagent models
A dynamic model of a multiagent system defines a probability distribution over possible system behaviors over time. Alternative representations for such models present tradeoffs i...
Quang Duong, Michael P. Wellman, Satinder P. Singh...
SAGA
2005
Springer
15 years 7 months ago
Dynamic Facility Location with Stochastic Demands
Abstract. In this paper, a Stochastic Dynamic Facility Location Problem (SDFLP) is formulated. In the first part, an exact solution method based on stochastic dynamic programming ...
Martin Romauch, Richard F. Hartl