Home > Publications . Search All . Browse All . Country . Browse PSC Pubs . PSC Report Series

PSC In The News

RSS Feed icon

Stephenson assessing in-home HIV testing and counseling for male couples

Thompson says mass incarceration causes collapse of Detroit neighborhoods

Liberal-conservative gap by education level growing in U.S.

Highlights

Maggie Levenstein named director of ISR's Inter-university Consortium for Political and Social Research

Arline Geronimus receives 2016 Harold R. Johnson Diversity Service Award

PSC spring 2016 newsletter: Kristin Seefeldt, Brady West, newly funded projects, ISR Runs for Bob, and more

AAUP reports on faculty compensation by category, affiliation, and academic rank

Next Brown Bag

PSC Brown Bags
will resume fall 2016

Sampling strategies for batch mode reinforcement learning

Publication Abstract

Fonteneau, Raphael, Susan A. Murphy, L. Wehenkel, and D. Ernst. 2013. "Sampling strategies for batch mode reinforcement learning." Revue d'Intelligence Artificielle, 27(2): 171-194.

We propose two strategies for experiment selection in the context of batch mode reinforcement learning. The first strategy is based on the idea that the most interesting experiments to carry out at some stage are those that are the most liable to falsify the current hypothesis about the optimal control policy. We cast this idea in a context where a policy learning algorithm and a model identification method are given a priori. The second strategy exploits recently published methods for computing bounds on the return of control policies from a set of trajectories in order to sample the state-action space so as to be able to discriminate between optimal and non-optimal policies. Both strategies are experimentally validated, showing promising results. © 2013 Lavoisier.

DOI:10.3166/RIA.27.171-194 (Full Text)

Browse | Search : All Pubs | Next