@techreport{2001266,
institution={University of Bristol},
author={Tim Kovacs},
number={CSTR-10-007},
title={Elaboration on the policy improvement theorem for soft policies in reinforcement learning},
bpages={5},
month={October},
year={2010},
abstract={In section 5.4 of their book on reinforcement learning Sutton and Barto show that the policy improvement theorem applies to soft policies, that is, when making a soft policy greedier (but still soft) with respect to its Q-function we obtain an improved policy.
I found this material difficult to follow and wrote this short document to elaborate on their proof. Familiarity with the material up until that section is assumed.},
abstract-url={http://www.cs.bris.ac.uk/Publications/pub_master.jsp?id=2001266},
keyword={Artificial Intelligence,Machine Learning},
pubtype={117}
}