Chapter 6 in Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto.

Here you will find experiments and results obtained when performing TD(lambda) learning on the random walk examples from this chapter using accumulating eligability traces and using replacing eligability traces.

This result similar to that presented in the book, but don't have the same scale. The conclusion that the replacing traces method does beat the accumulating trace method holds true however.

John Weatherwax

Last modified: Sun May 15 08:46:34 EDT 2005