Chapter 11
arash haratian
4/18/2021
Baird’s counterexample
source("./counterexample.R")Figure 11.2: Demonstration of instability on Baird’s counterexample
plot_fig11.2()
Figure 11.5: The behavior of the TDC algorithm
plot_fig11.5()
Figure 11.6: The behavior of the one-step Emphatic-TD algorithm in expectation
plot_fig11.6()