58 search results - page 9 / 12 » A Dynamic Allocation Method of Basis Functions in Reinforcem... |
NIPS
1996
13 years 9 months ago
1996
Although TD-Gammon is one of the major successes in machine learning, it has not led to similar impressive breakthroughs in temporal difference learning for other applications or ...
JCP
2007
13 years 7 months ago
2007
Abstract— We describe a general method to transform a non-Markovian sequential decision problem into a supervised learning problem using a K-bestpaths algorithm. We consider an a...
CIG
2005
IEEE
14 years 1 months ago
2005
IEEE
A newly designed game is introduced, which feels like Backgammon, but has a simplified rule set. Unlike earlier attempts at simplifying the game, Nannon maintains enough features a...
ML
1998
ACM
13 years 7 months ago
1998
ACM
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
KDD
1998
ACM
13 years 11 months ago
1998
ACM
This paper develops the concept of usefulness in the context of supervised learning. We argue that usefulness can be used to improve the performance of classification rules (as me...