Two Kinds of Training Information for Evaluation Function Learning (1991)

by Paul E. Utgoff , Jeffery A. Clouse
Venue:In Proceedings of the Ninth Annual Conference on Artificial Intelligence
Citations:54 - 3 self

Active Bibliography

6 Feature Discovery for Inductive Concept Learning – Tom Fawcett - 1993
STD(λ): learning state differences with TD(λ) – Lex Weaver, Jonathan Baxter
STD (  ): learning state differences with TD (  ) – Lex Weaver
3 Learning From State Differences: – Lex Weaver, Jonathan Baxter - 1999
7 Reinforcement Learning From State and Temporal Differences – Lex Weaver, Jonathan Baxter - 1999
363 Practical Issues in Temporal Difference Learning – Gerald Tesauro - 1992
12 Statistical feature combination for the evaluation of game positions – Michael Buro - 1995
6 A Game-Learning Machine – Michael Gherrity - 1993
24 Learning Subjective Functions with Large Margins – Claude-nicolas Fiechter, Seth Rogers - 2000
3 Tuning evaluation functions by maximizing concordance – D. Gomboc, M. Buro, T. A. Marsland
5 Recent Advances in Machine Learning and Game Playing – Johannes Fürnkranz - 2007
109 Co-Evolution in the Successful Learning of Backgammon Strategy – Jordan B. Pollack, Alan D. Blair - 1998
2 Learning Evaluation Functions – Justin A. Boyan, Scott E. Fahlman, Tom Mitchell - 1996
4 Experience-Based Creativity – Robert Levinson - 1991
17 Automated Learning of Load-Balancing Strategies For A Distributed Computer System – P. Mehra, Load Balancing As, A Strategy-learning Task - 1992
32 Modular Neural Networks for Learning Context-Dependent Game Strategies – Justin A. Boyan - 1992
3 Learning to Play Games From Experience: An Application of Artificial Neural Networks and Temporal Difference Learning – Daniel Kenneth Olson - 1993
Load Balancing as a Strategiy-Learning Task – n.n. - 1992
1 A New Approach to Genetic-Based Automatic Feature Discovery – Terry B. Van Belle - 1995