Conservative and Greedy Approaches to Classification-based Policy Iteration - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2012

Conservative and Greedy Approaches to Classification-based Policy Iteration

Mohammad Ghavamzadeh
  • Function : Author
  • PersonId : 868946
Alessandro Lazaric


The existing classification-based policy iteration (CBPI) algorithms can be divided into two categories: {\em direct policy iteration} (DPI) methods that directly assign the output of the classifier (the approximate greedy policy w.r.t.~the current policy) to the next policy, and {\em conservative policy iteration} (CPI) methods in which the new policy is a mixture distribution of the current policy and the output of the classifier. The conservative policy update gives CPI a desirable feature, namely the guarantee that the policies generated by this algorithm improve at each iteration. We provide a detailed algorithmic and theoretical comparison of these two classes of CBPI algorithms. Our results reveal that in order to achieve the same level of accuracy, CPI requires more iterations, and thus, more samples than the DPI algorithm. Furthermore, CPI may converge to suboptimal policies whose performance is not better than DPI's.
Fichier principal
Vignette du fichier
Ghavamzadeh.pdf (133.7 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00772610 , version 1 (10-01-2013)


  • HAL Id : hal-00772610 , version 1


Mohammad Ghavamzadeh, Alessandro Lazaric. Conservative and Greedy Approaches to Classification-based Policy Iteration. AAAI - 26th Conference on Artificial Intelligence, Jul 2012, Toronto, Canada. ⟨hal-00772610⟩
213 View
110 Download


Gmail Facebook X LinkedIn More