Sciweavers

209 search results - page 30 / 42
» Optimization and Convergence of Observation Channels in Stoc...
Sort
View
IJCAI
2003
13 years 9 months ago
A Planning Algorithm for Predictive State Representations
We address the problem of optimally controlling stochastic environments that are partially observable. The standard method for tackling such problems is to define and solve a Part...
Masoumeh T. Izadi, Doina Precup
ICML
2000
IEEE
14 years 9 months ago
Reinforcement Learning in POMDP's via Direct Gradient Ascent
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
Jonathan Baxter, Peter L. Bartlett
GECCO
2007
Springer
160views Optimization» more  GECCO 2007»
14 years 2 months ago
An analysis of constructive crossover and selection pressure in genetic programming
A common problem in genetic programming search algorithms is destructive crossover in which the offspring of good parents generally has worse performance than the parents. Design...
Huayang Xie, Mengjie Zhang, Peter Andreae
JSAC
2007
189views more  JSAC 2007»
13 years 8 months ago
Non-Cooperative Power Control for Wireless Ad Hoc Networks with Repeated Games
— One of the distinctive features in a wireless ad hoc network is lack of any central controller or single point of authority, in which each node/link then makes its own decision...
Chengnian Long, Qian Zhang, Bo Li, Huilong Yang, X...
CORR
2007
Springer
73views Education» more  CORR 2007»
13 years 8 months ago
Universal Reinforcement Learning
—We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence futu...
Vivek F. Farias, Ciamac Cyrus Moallemi, Tsachy Wei...