Constructive Function Approximation TITLE2:

Authors:
Paul E. Utgoff;Doina Precup
Affiliations:
-;-
Venue:
Constructive Function Approximation TITLE2:
Year:
1997

Citing 0
Cited 5

Improving heurisitic mini-max search by supervised learning

Artificial Intelligence - Chips challenging champions: games, computers and Artificial Intelligence
Learning Game-Specific Spatially-Oriented Heuristics

Constraints
Building a Basic Block Instruction Scheduler with Reinforcement Learning and Rollouts

Machine Learning
From Simple Features to Sophisticated Evaluation Functions

CG '98 Proceedings of the First International Conference on Computers and Games
Learning from Perfection. A Data Mining Approach to Evaluation Function Learning in Awari

CG '00 Revised Papers from the Second International Conference on Computers and Games

Quantified Score

Hi-index	0.00

Visualization

Abstract

Algorithm ELF is a nonlinear function approximator that constructs features as necessary while it updates its representation of the function that it is learning to approximate. Feature construction is guided by representational inadequacy that is associated with particular values of the base-level variables. The features have a logical form, making them easy to interpret.