Sciweavers

Share
35 search results - page 1 / 7
» Using Temporal Neighborhoods to Adapt Function Approximators...
Sort
View
IWANN
1999
Springer
9 years 8 months ago
Using Temporal Neighborhoods to Adapt Function Approximators in Reinforcement Learning
To avoid the curse of dimensionality, function approximators are used in reinforcement learning to learn value functions for individual states. In order to make better use of comp...
R. Matthew Kretchmar, Charles W. Anderson
ICML
2006
IEEE
9 years 9 months ago
Automatic basis function construction for approximate dynamic programming and reinforcement learning
We address the problem of automatically constructing basis functions for linear approximation of the value function of a Markov Decision Process (MDP). Our work builds on results ...
Philipp W. Keller, Shie Mannor, Doina Precup
CG
2000
Springer
9 years 8 months ago
Chess Neighborhoods, Function Combination, and Reinforcement Learning
Abstract. Over the years, various research projects have attempted to develop a chess program that learns to play well given little prior knowledge beyond the rules of the game. Ea...
Robert Levinson, Ryan Weber
JMLR
2010
119views more  JMLR 2010»
8 years 10 months ago
A Convergent Online Single Time Scale Actor Critic Algorithm
Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their gen...
Dotan Di Castro, Ron Meir
ATAL
2005
Springer
9 years 9 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
books