next up previous
Next: The algorithm using Monte Up: Large State Space Previous: Example showing that tied

   
Approximate Policy Iteration

The general structure is the same as in the Policy Iteration, except the following differences:
Those two differences are a source for an error.
  
Figure: Regular Policy Iteration
\begin{figure}\psfig{file=Policy.ps,width=4in,clip=}
\end{figure}


  
Figure: Approximate Policy Iteration
\begin{figure}\psfig{file=PolicyApp.ps,width=4in,clip=}
\end{figure}



 

Yishay Mansour
2000-01-11